Skip to content
View virenbajaj's full-sized avatar

Block or report virenbajaj

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
virenbajaj/README.md

Hi there 👋

Senior ML Engineer at CVS Health — building production LLM systems for health insurance (RAG, agents, evaluation at scale).

Now

  • CSR-facing agentic RAG system for health-benefits Q&A
  • UQLM — LLM hallucination detection via uncertainty quantification (JMLR 2026, 1.2K+ ⭐)
  • LangFair — bias & fairness evaluation for LLM use cases (JOSS 2025)

Previously

  • Led Conduit — CLI for deploying Kubeflow pipelines to GCP, adopted by 13 teams (PyData NYC 2023)
  • NASA Langley: RL for formally verified sense-and-avoid (IEEE DASC 2019) + RF interference detection for autonomous drones
  • CMU: verifiably safe SCUBA diving with formal methods (ACM EMSOFT 2019)
  • GlueX Collaboration @ Jefferson Lab: proton–antiproton photoproduction analysis (APS DNP 2017)
  • M.S. CS (ML) @ Columbia · B.S. Physics @ CMU

📄 Google Scholar · 💼 LinkedIn

Pinned Loading

  1. cvs-health/uqlm cvs-health/uqlm Public

    UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection

    Python 1.2k 128

  2. cvs-health/langfair cvs-health/langfair Public

    LangFair is a Python library for conducting use-case level LLM bias and fairness assessments

    Python 260 46

  3. ravishrawal/NFT-GAN ravishrawal/NFT-GAN Public

    Jupyter Notebook

  4. ravishrawal/the-carbon-implication-of-crypto ravishrawal/the-carbon-implication-of-crypto Public

    JavaScript

  5. PredictingRatings PredictingRatings Public

    Implement a gaussian matrix factorization model and use MAP estimation on the MovieLens dataset to predict the rating a user would give to an unseen movie.

    Jupyter Notebook

  6. Q-LearningTutorial Q-LearningTutorial Public

    In this tutorial we learn how to find an optimal path from one node of a graph to another using Q-learning.

    Jupyter Notebook 1