Srijith Rajamohan, Ph.D.

AI/ML Scientist

Blacksburg, VA 24060

srijith.rajamohan@databricks.com

Education

2009-2014 Ph.D. in Computational Engineering The University of Tennessee
Dissertation: ”A StreamlineUpwind/ Petrov-Galerkin FEM based Time-Accurate Solution of 3D Time-Domain Maxwell’s Equations for Dispersive Materials”

2007-2009 MS in Electrical Engineering The Pennsylvania State University
Thesis: ”A Neural Network based classifier on the Cell Broadband Engine”

Core Competencies

• HPC - HPC, FEM, Eigen, PetSc, MPI, OpenMP, CUDA, OpenACC
• Deep Learning - NLP/NLU, Unsupervised and Weakly-supervised learning
• Machine Learning - Network analysis, Bayesian inference
• Bayesian Learning/Probabilistic Programming - PyMC3
• Deep Learning Frameworks - Tensorflow, Pytorch, Keras, Scikit-learn
• DataScience - Pandas, NumPy, SciPy, Nlopt, PySpark, Airflow, RQ
• Scientific Visualization - Visit, ParaView, VTK
• Information Visualization - Plot.ly, Matplotlib, Bokeh, Tableau
• Languages - C, C++, Python, Fortran
• Database/Datalake - MongoDB, SQL, Delta Lake
• Workflow management - Git, Ansible
• MLOps - MLflow, Neptune.ml, Comet.ml

Experience (selected)

2020-Present Senior Developer Advocate (Data Science & ML), Databricks, Blacksburg, VA

2014-2020 Computational Scientist, Advanced Research Computing, Blacksburg, VA

2009-2014 Graduate Research Assistant, SimCenter: Center of Excellence in Computational Engineering, The University of Tennessee, Chattanooga, TN

2007-2009 Graduate Student, The Microsystems Design Lab, The Pennsylvania State University, State College, PA

Sr. Developer Advocate (Data Science/Machine Learning)

My role as a Developer Advocate in Data Science allows me to serve as a thought leader in Machine learning and Data science, and educate the community about the state-of-the-art. This role allows me to engage in internal advocacy, and work cross-functionally across various units such as product management, product marketing, solutions, engineering and documentation. Some of my responsibilities include:

• - Thought leadership articles and presentations on enterprise and open-source ML/Data Science
• - Provide guidance and feedback to product management and product marketing
• - Act as a subject matter expert to the solutions and engineering team

My technical areas of expertise here are Deep Learning for Natural Language Understanding (NLU), Bayesian inference and large-scale processing using PySpark.

Links: = Webpage of project

Projects

2021 Lead the DevRel efforts on Machine Learning at Databricks

• - Engage with all stakeholders, i.e. everyone from the executive team to the practitioner community to identify their ML needs and help provide solutions.
• - Guide the ML/DS Product Management team with regards to product features
• - Work with the Product Marketing Managers to help reach the appropriate community of practitioners
• - Understand the needs of the practitioner community

2021 Apache Spark

• - Lead the efforts on growth and the messaging architecture of Spark and Koalas
• - Engage with C-suite executives to define the growth strategy for Spark
• - Offer strategic guidance on improvements to the Spark website and documentation, and grow community adoption

2021 Lead the advocacy efforts on OSS MLflow

• - Interface with the Mlflow product team at Databricks and drive adoption of OSS MLflow among the practitioner community

2020-Present Authored a set of three courses on Bayesian Inference titled ‘Introduction to Computational Statistics for Data Scientists’ on Coursera

• - A practical guide to getting started with scalable Bayesian Inference using PyMC3
• - Introduction to Bayesian Statistics
• - Bayesian Inference with MCMC
• - PyMC3 for Bayesian Modeling and Inference

2020-Present Articles on Data Science and Machine Learning

• - GPU-accelerated Sentiment Analysis Using Pytorch and Huggingface on Databricks
• - Are GPUs really expensive? A benchmark study for inference in NLP
• - An Experimentation Pipeline for Extracting Topics From Text Data Using PySpark
• - MLflow for Bayesian Experiment Tracking
• - Bayesian Modeling of the Temporal Dynamics of COVID-19 using PyMC3
• - Using Bayesian Hierarchical Models to Infer the Disease Parameters of COVID-19
• - Beyond LDA: Dive into BigARTM for Topic Modeling
• - The Modern Chief Data Officer: Transitioning From Defense to Offense
• - Reproduce Anything: Machine Learning meets Data Lakehouse

2020-Present Presentations/Talks
Machine Learning at Scale (Nov/Aug 2021)

• - Best practices for the full lifecycle of ML projects along with issues such as reproducibility, explainability, trustworth AI and governance
• - Keynote at the IEEE IDSTA conference
• - Invited talk at the ADBIS workshop

Deep Learning at Scale at Databricks (Oct 2021)

• - Presentation on how to scale Deep learning workloads at Databricks at the Big Data Symposium in South Korea

MLflow for the ML Lifecycle (Nov 2021)

• - Presentation on how to use OSS MLflow for model management, reproducibility with MLflow projects and Model registry, and model nference/serving

Bayesian Modeling of the Temporal Dynamics of COVID-19 using PyMC3 at the Data+AI Summit (Nov 2020)

• - Bayesian inference to estimate the disease parameters of COVID-19 from real case data with PyMC3

Presented ‘Maintable HPC and Data Science with Python/C++’ at the National Center for Atmospheric Research (NCAR) (Mar 2021)

• - Scale HPC and Data Science codes written in Python
• - JIT approach using Numba
• - Offload compute-intensive portions of the Python code using Eigen and Xtensor in C++

Computational Scientist

This role as a Computational Scientist involved providing Scientific Computing expertise, enabling High-Performance Computing and Visualization solutions and performing research in Machine Learning.

Links: = Webpage of project

Research Projects

2019-Present Interactive Network Analysis of Social Graphs

• - Network analysis of social media network of political figures in collaboration with the Political Science dept.
• - Network data obtained from Twitter, ETL workflows performed with PySpark and saved in Spark tables
• - Metabase as a BI dashboard for the SME to perform EDA on these tables
• - Networks graphs created using Graphtools
• - Interactive visualization with Sigma.js in the web browser
• - Distributed Deep learning sentiment analysis pipeline with Huggingface Roberta embeddings

2018-Present Natural Language Processing for determining Political Affiliation

• - Stance extraction from a weakly-supervised classifier through a word vector-based approach to
  determine political affiliation
• - Tweets were stored and preprocessed in MongoDB
• - Python RQ for data acquisition
• - PySpark and Spacy used for corpus cleaning
• - Fixed embedding generation frameworks such as Doc2Vec and Fasttext used for training and generation
  of sentence embeddings
• - Contextual embeddings such as Elmo for generating sentence embeddings
• - Self-attention for model interpretability
• - Created interactive web-based visualization tool for stance visualization
• - Hyperparameter optimization with Comet.ml
• - Apache Airflow to streamline the workflow

2019-Present Deep Learning lead for the project ‘Eye Gaze tracking for Surgical Training’

• - Oversaw a team of 5 attempting to learn gaze patterns of resident surgeons using Deep Learning
• - Collaboration between the ISE department at Virginia Tech and the Carilion School of Medicine

2019-2020 Co-PI on Jefferson National Lab funded project ‘Next-generation Visual Analysis Workspace for Multidimensional Nuclear Femtography Data’

• Joint venture between Virginia Tech and JLab
• - Visual Analytics project for Nuclear Femtography data.
• - Big Data analytics and visualization: Investigating various novel ways to enable understanding of nuclear physics phenomena with two-dimensional and three-dimensional visualizations.

2015-2020 General Dynamics Collaboration with the Discovery Analytics Center(VT)

• - Computational statistics and dimensionality reduction using unsupervised techniques such as PCA, MDS
• - Weighted Multi-Dimensional Scaling (WMDS) for semantic interaction
• - Formulated a highly-accurate Backward MDS algorithm
• - Formulated and implemented the optimization scheme for the solution of Inverse MDS in Python using the NLopt optimization package
• - Parallelized Inverse MDS Python code using Numba
• - Accelerated Inverse MDS C++ code for low latency with Eigen

2019-2020 Generative Methods for Stance Detection and Visualization

• - Investigate Variational Autoencoders for extracting stance
• - Use static and contextual text embeddings with this configuration
• - Use a semi-supervised learning approach with partially labeled data

2019-2019 Reinforcement learning for Eye Tracking in Laparoscopic Surgery

• - Reinforcement learning for learning eye gaze patterns in surgeons during laparoscopic surgery
• - ADNet for training the reinforcement learning algorithm
• - The algorithm attempts to learn expert gaze patterns that can then be used to train and evaluate residents

2019 Cost analysis of On-premise Cloud vs. Public Cloud for Virginia Tech

• - Performed a cost analysis of Virginia Tech’s on-premise cloud and compared it to those offered
  by third-party external cloud providers for scientific computing.
• - This was done to understand the tradeoffs of an on-premise cloud for Virginia Tech stakeholders,
  i.e. the VT research and academic community since their needs are unique.
• - Created an interactive report that allows end-users to compare the costs based on their usage needs.

2018-2019 ICAT SEAD Grant 2018

• - Co-PI on ICAT SEAD grant to analyze and visualize the health and nutrition policies across countries
• - Interdisciplinary collaboration with the Health and Nutrition, Business and SOVA departments
• - Visualization of geographic food policy data
• - Developing an open-source interactive visual query framework
• - Web-based framework that is deployed with Docker
• - Funding used to hire undergraduate intern from the CMDA department as part of a broader
  engagement program for this project.

2018-2019 Scheduling and Visualization Application for Idaho National Lab

• - Built a Django and D3 based scheduling and visualization tool
• - Tool helps the Idaho National Lab manage outage tasks for the Nuclear Power plants
• - Managed two undergrads in this development project

2016-2017 HNFE Project for Visualization of National Food and Beverage Endorsements

• - Collaborated with the HNFE department to visualize data
• - Produced interactive web-based visualizations for exploratory analysis of Food and Beverage endorsements
• - Work was presented to policy makers to understand the impact of celebrity endorsements
• - Produced a web-based analytics framework for visual querying of endorsement data
• - Framework extended using Dask for analyzing Big Data

2016-2017 Interactive 3D Visualization for Nuclear Reactor Pool

• - Multi-user user interactive visualization using open-source technology (X3D) in web browsers
• - This involved collaborating with the Nuclear Engineering department to interface with their
  RAPID toolset to generate a visualization and querying tool.

Infrastructure projects

Cloud Computing

• - Played a key role in architecting the cloud computing infrastructure for research computing using Openstack at Virginia Tech
• - Involved in designing and setting up Cloud Computing best practices and architectures
• - Compiled document for Cloud Computing use-cases comparing OpenStack, LXC and Docker containers

Scientific Visualization

• - ParaView and Visit for Massive Scientific Visualization Streamlined remote rendering on ParaView using the ARC supercomputers
• - Set up Python-based scripted visualization and used this for profiling the remote rendering capabilities of ParaView
• - Compiled a ’Best Practices’ document for Massive Scientific Visualization using ParaView on the VT clusters
• - Evaluating novel approaches for scientific visualization using ParaView and Visit

Collaborative Computing Platforms

• - Setup Visionarium resources ’Anvil’, ’Polaris’, ‘Pluto’, ‘Spock’ as collaborative-computing platforms
  for Data Science users and project collaborators using JupyterHub. Set up policies for group access
  and compute resources on these machines
• - Setup unified Python environments with the Python Data Science stack (E.g. Numpy, SciPy, Plot.ly, Pandas, Numba)
• - Setup Machine Learning and Deep Learning environments with Tensorflow, Keras and Pytorch to run on GPUs.
• - Setup out-of-core computing with Dask and GPU compute with CUDA

Miscellaneous

• • Set up Asana project management tools for Visualization team’s internal coordination and communication
• • Setup GitLab Continuous Integration as part of code-quality improvement in research projects. Authored blog post on this topic.
• • Setup and leading the adoption of Open Science Framework as a provenance and data management tool for research projects
• • Participated in several NSF proposals
• • Provide Visionarium Tours for Virginia Tech users and external visitors
• • Helped set up Virginia Tech ARC Booth and Slideshow presentations at SuperComputing 2016, 2017
• • Virginia Tech campus champion for XSEDE
• • Virginia Tech representative for ACI-REF
• • Poster and paper reviewer for XSEDE15, XSEDE16, PEARC17 and PEARC18
• • Session Chair for Workforce Development and Diversity XSEDE2016
• • NSF Proposal reviewer
• • Supervising ARC GRAs

Graduate School

Highlighted is some of my research work conducted during my Masters and Ph.D. programs.

Graduate Research Assistant

2009-2014 Experience developing and maintaining a 3D Time domain Electromagnetic solver for open/closed boundary problems such as Radar Cross Sections, Waveguides, Frequency-dependent materials etc. Knowledge of Finite Element Method for solving electromagnetic problems involving time-dependent phenomena.

• - Acceleration of EM Fortran code by interfacing with CUDA C.
• - Implemented Linear System solvers both serial and parallel-Block GMRES, Block Gauss Seidel,
  LU in C and Fortran.
• - Written 2D and 3D CFD implicit unstructured Finite Volume solver in C++ using the Van Leer Flux and Roe Flux.
• - Computational design of airfoils and sensitivity analysis.
• - Delaunay triangulation of 2D meshes in C++.
• - Mesh smoothing using Winslow and Linear Elastic smoothing in C++.
• - Mentored two graduate students in Computational Engineering.
• - Pointwise for mesh generation.

Graduate Student

2007-2009 I was a member of the Microsystems Design Lab at the Pennsylvania State University where I worked on accelerator technology.

• - Implemented a neural network for skin-tone detection on the IBM Cell and observed a 23x speedup over
  the serial code (Masters thesis).

Summer Intern

2008 Performed code maintenance and bug fixes on proprietary embedded system firmware at Arris Corporation.

Teaching

2019 SuperComputing 2019 short talks : Talks@VT series

• - Introduction to Generative Modeling
• - Cloud Cost Comparison: On-premise vs. External Vendor

2019 Presented work on Stance Detection using Deep Learning at the AI4Good workshop held at PEARC19

2018 SuperComputing 2018 short talks : Talks@VT series

• - Deep Learning on GPUs with PyTorch for Text Analysis
• - AutoML: An Overview of Automated Machine Learning

2018 Taught ‘Text Summarization with Word Embeddings using PyTorch’ for CS4984/5984 in Fall 2018

2016 Workshops for the Industrial and Systems Engineering Dept.

• - Introduction to Scientific Python: 150 min handson workshop
• - Introduction to Data Visualization with Plot.ly: 150 min handson workshop

2016 Taught undergraduate class ‘CS1064: Introduction to Python’ in the Spring 2016 semester

2016 Taught ’Introduction to OpenACC’ lecture for undergraduate class ‘CMDA 3634: Comp Sci Foundations for CMDA’

2018 Taught workshop titled ’Introduction to ARC Cloud using OpenStack for Machine Learning’

2015-2019 Taught Networked Learning Initiative Seminar classes 2015, 2016, 2017 and 2018

• - Introduction to Scientific Computing using Python
• - Introduction to Data Visualization
• - Co-taught ’Introduction to Debugging and Profiling with GNU tools’
• - Introduction to CUDA
• - Introduction to Scientific Visualization using ParaView
• - TensorFlow for Machine Learning
• - Dask for Out-of-Core Computing: Big Data solutions on your laptop
• - Unsupervised Machine Learning using Sckit-learn and TensorFlow
• - Supervised Machine Learning using Sckit-learn and TensorFlow
• - Deep Learning using TensorFlow and Keras

2015-2016 Taught XSEDE workshops in 2015, 2016

• - Introduction to Scientific Computing using Python
• - Python Pandas for Data Analytics

2017-2018 PEARC workshops in 2017, 2018

• - A Data Scientist’s Python Toolbox
• - Workshop titled ’Introduction to Machine Learning’ taught at PEARC18

2015-Present Mentored graduate and undergraduate students on various funded projects

Publications

*- Chaitanya S. Kulkarni, Tianzi Wang, Nathan Lau, Jacob Hartman-Kenzler, Sarah E. Parker, Srijith Rajamohan, Laura E. Barnes, Shawn D. Safford, Applying Deep Learning to Provide Eye- Gaze Guidance for the Peg Transfer Task, Jan 1 2021, 16th Academic Surgical Congress

- Srijith Rajamohan, Robert Settlage Informing the On/Off-prem Cloud Discussion in Higher Education, PEARC20, ACM, Portland

- Robert Settlage, Srijith Rajamohan Enabling AI/DL Workloads on HPC Infrastructure through Containers and Open OnDemand. HPCKP20, High-Performance Computing Knowledge Meeting, Barcelona, July 2020

- Rincón-Gallardo Patiño, Sofía, Srijith Rajamohan, Kathleen Meaney, Eloise Coupey, Elena Serrano, Valisa E. Hedrick, Fabio da Silva Gomes, Nicholas Polys, and Vivica Kraak. Development of a Responsible Policy Index to Improve Statutory and Self-Regulatory Policies that Protect Children’s Diet and Health in the America’s Region. International Journal of Environmental Research and Public Health 17, no. 2 (2020): 495.

- Robert Settlage, Srijith Rajamohan, Kevin Lahmers2, Alan Chalker3, Eric Franz3, Steve Gallo4, David Hudak3. Portals for Interactive Steering of HPC Workflows. Nov 2019, Third Workshop on Interactive High-Performance Computing, SC19

- Srijith Rajamohan, Alana Romanella, Amit Ramesh. A Weakly-Supervised Attention-based Visualization Tool for Assessing Political Affiliation. Aug 2019, arXiv:1908.02282 [cs.CL], https:// arxiv.org/abs/1908.02282

- Zhou, M., Rajamohan, S., Hedrick, V., Rincón-Gallardo Patiño, S., Abidi, F., Polys, N., & Kraak, V. (2019). Mapping the Celebrity Endorsement of Branded Food and Beverage Products and Marketing Campaigns in the United States, 1990–2017 ,International journal of environmental research and public health 16.19 (2019): 3743

- Valerio Mascolino, Alireza Haghighat, Nicholas Polys, Nathan J. Roskoff, and Srijith Rajamohan. 2019. A Collaborative Virtual Reality System (VRS) with X3D Visualization for RAPID, The 24th International Conference on 3D Web Technology (Web3D ’19), ACM, New York, NY, USA, 1-8.

- Srijith Rajamohan and Faiz Abidi, Web-based Visualization and Querying of Food and Beverage Endorsements by Celebrities, PEARC19, ACM, Chicago

- Rajamohan, S., Romanella, A., Ramesh, A., A Human-in-the-Loop Deep Learning Based Document Tagging for Stance Detection, CHCI 2019: Algorithms that make you think, Blacksburg.

- Rajamohan,S. and Anderson, W.K. A Modified Streamline Upwind/Petrov-Galerkin Stabilization Matrix for Time-Domain FEM, ACES 2018, Denver

- Rajamohan,S. and Anderson, W.K. Using an Approximate Streamline Upwind/Petrov-Galerkin Stabilization Matrix for the Solution of Maxwell’s Equations in Dispersive Materials, ACES 2018, Denver.

- Abidi, F., Polys, N., Rajamohan, S., Arsenault, L., Mohammed, A. (2018, April). Remote high performance visualization of big data for immersive science. In Proceedings of the High Performance Computing Symposium (p. 5). Society for Computer Simulation International.

- Zhou M, Kraak VI, Rajamohan S, Abidi F, Polys N. Mapping the Celebrity Marketing of Branded Food and Beverage Products in the United States: Policy Implications and Research Needs. 15th World Congress on Public Health. April 3-7, 2017. Melbourne, Victoria, Australia

- Nicholas Polys, Ayat Mohammed, Jagathshree Iyer, Peter Radics, Faiz Abidi, Lance Arsenault, and Srijith Rajamohan. Immersive Analytics: Crossing the Gulfs with High-Performance Visualization. IEEE VR 2016 Workshop on Immersive Analytics

- Rajamohan,S and Anderson, W.K , HPC for Legacy EM Code, a Mixed Language Approach using CUDA. Applied Computational Electromagnetic Society 2012, Volume: GPU for CEM.

- Porting Algorithms to the IBM Cell Processor - an FFT case study. Penn State Research Symposium 2009.