Skip to content
View thiruselvaa's full-sized avatar

Block or report thiruselvaa

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.

Content in all repositories owned by your account will be closed.
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
thiruselvaa/README.md

Hi, I'm Selvaa 👋

Principal Engineer at Optum/UnitedHealth Group's Chief Data Office, transitioning 24+ years of engineering experience into AI/ML and Agentic AI.

  • 🤖 Building ADPA ("Optimus Prime") — an Agentic-AI platform that turns a data contract into a production-ready data product on Azure Databricks/Snowflake in hours instead of weeks (114K+ lines, 2,900+ tests, placed 3rd in company-wide in an internal AI innovation event)
  • 🧠 Recently completed the MIT Professional Education Applied Data Science Program (Leveraging AI for Effective Decision-Making) and a Generative AI certification
  • 🏗️ Background in Data Mesh architecture, Azure Databricks, Apache Kafka/Spark, and large-scale Hadoop/Big Data systems
  • ⚙️ Founding engineer of a Go-based streaming filter library with a custom filter DSL (nested boolean/array logic, EBaaS caching, CLI tooling) — still powering 35+ production applications today
  • 📜 Named inventor on a submitted patent for a rule-based runtime transformation layer for FHIR healthcare data
  • 🎓 Diamond Bravo Award recipient for mentoring an early-career team through a Care Coordination & Referral Tracking microservice capstone in Optum's Technology Development Program (TDP) Bootcamp
  • 🚀 Currently exploring: LangGraph, multi-agent systems, RAG architectures
  • 📊 Built and benchmarked recommender systems (SVD, KNN, matrix factorization) on the Amazon Electronics dataset as part of the MIT program, reaching RMSE 0.8808 and F1@10 0.869 on tuned models

Core stack: Python · Scala · Go · TypeScript · LangGraph · Apache Spark · Kafka · Databricks · Snowflake · Apache Iceberg · Terraform · Kubernetes · HL7 FHIR · scikit-learn · TensorFlow · pandas · NumPy

📫 Reach me: LinkedIn · thiruselvaa@gmail.com


GitHub Stats Top Langs

Popular repositories Loading

  1. shimmy shimmy Public

    Forked from Michael-A-Kuykendall/shimmy

    ⚡ Python-free Rust inference server — OpenAI-API compatible. GGUF + SafeTensors, hot model swap, auto-discovery, single binary. FREE now, FREE forever.

    Rust 2

  2. gofr gofr Public

    Forked from gofr-dev/gofr

    An opinionated Go framework for accelerated microservice development

    Go 1

  3. yokai-worker-template yokai-worker-template Public

    Go 1

  4. duckdb-pipeline duckdb-pipeline Public

    Forked from pracdata/duckdb-pipeline

    Demonstrating the capabilities of DuckDB as a transformation engine for data lakes

    Python 1 1

  5. AIAgentExamples AIAgentExamples Public

    Forked from ChengzhiZhao/AIAgentExamples

    Examples For AI Agent

    Jupyter Notebook 1

  6. evidently evidently Public

    Forked from evidentlyai/evidently

    Evidently is ​​an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.

    Jupyter Notebook 1