Omkar Nayak

Hi, I'm Omkar Nayak.

A Scientist

Self-driven, quick starter, passionate programmer with a curious mind who enjoys solving complex and challenging real-world problems.

About

Hello everyone, I'm Omkar, a Mathematics and Computer Science Student at the University of Michigan - Ann Arbor. My interest is currently exploring the applications of Machine Learning and Artificial Intelligence in various domains such as Healthcare and Energy Infrastructure. I'm currently a Machine Learning Engineer at Synafox AI and Research Associate II at Zhou Lab. At Synafox AI, I develop autonomous agentic workflows to build clean energy infrastructure and at Zhou Lab, I'm working on publishing 2 papers in Integrating expert reasoning into Large Language Models (LLMs) and a novel phenotype recognition method for Genome Wide Association Studies (GWAS).

In my free time, I enjoy playing basketball (and recently got into lifting), really like watching horror movies, and making sweet treats!

Languages: Python, MATLAB, C, C++, JavaScript, HTML/CSS, Bash
Frameworks: CrewAI, Langgraph, LangChain, Flask, Apache
Databases: MySQL, PostgreSQL, NoSQL
Libraries: PyTorch, TensorFlow, SciPy, MLflow, OpenCV, Scikit-learn, Keras, PyTorch Geometric
Tools & Technologies: Git, Docker, AWS, Azure

Projects

                
Autonomous Energy Infrastructure Agent
                  Multi-agent system using CrewAI for monitoring and optimizing clean energy infrastructure through digital twin simulations.
                
Project DetailsTools: CrewAI, LangChain, Python, Docker
Autonomous monitoring of digital twin simulations
Predictive model optimization for resource allocation
MLOps integration with CI/CD pipeline

Production RAG Pipeline
                  Scalable RAG pipeline using LangChain and vector databases for domain-specific LLM applications.
                
Project DetailsTools: LangChain, Vector Databases, Python, FastAPI
Low-latency context-aware inference
Enterprise-grade scalability
Domain-specific knowledge integration

LLM-Enhanced GWAS Analysis
                  Novel phenotype recognition method using LLMs for Genome Wide Association Studies with 50,000+ genetic records.
                
Project DetailsTools: Python, PyTorch, LangChain, PubMed API
Tested on 12 distinct phenotypes
50,000+ genetic sequencing records analyzed
Electronic Health Records integration

Expert Reasoning in Medical LLMs
                  Integrating expert medical reasoning into LLMs, improving diagnostic accuracy by 38% on 80,000+ health records.
                
Project DetailsTools: Python, vLLM, NeMo Guardrails, PyTorch
38% improvement in diagnostic accuracy
80,000+ precision health records analyzed
HIPAA-compliant implementation

Computer Vision Pipeline
                  Advanced computer vision system using PyTorch and OpenCV for real-time object detection and analysis.
                
Project DetailsTools: PyTorch, OpenCV, Python, CUDA
Real-time object detection
Custom neural network architecture
GPU-accelerated processing

MLOps Automation Platform
                  End-to-end MLOps platform with automated model training, validation, and deployment using MLflow and Docker.
                
Project DetailsTools: MLflow, Docker, Kubernetes, Python
Automated model lifecycle management
Continuous integration and deployment
Model performance monitoring

Experience

Synafox AI

Machine Learning and Systems Engineer

Designed and developed autonomous agentic workflows using CrewAI for the continuous monitoring and optimization of digital twin simulations improving the management of predictive models for system analysis and resource allocation.
Integrated of multiple Agentic Frameworks into the CI/CD pipeline, automating the software development cycle by using MLOps principles to minimize manual intervention and accelerate the Agile iteration frequency.
Deployed scalable, production-grade RAG pipelines using LangChain and vector databases to serve domain-specific LLMs. This architecture ensured low-latency, context-aware inference for specialized enterprise applications.
Tools: Python, CrewAI, LangChain

May 2025 - Present | Detroit, Michigan

Zhou lab @University of Michigan

Research Assistant II

Enhanced Genome Wide Association Studies (GWAS) at the UM School of Public Health by authoring a paper on a novel phenotype recognition method, the bespoke Large Language Models (LLMs) successfully tested on 12 distinct phenotypes from over +50,000 Genetic Sequencing and Electronic Health Records.
Advanced Deep Learning diagnostic accuracy by about 38% by collaborating on a paper within a cross-functional team of doctors at Michigan Medicine to integrate expert reasoning into LLMs. This work analyzed +80,000 precision health records from +24,000 patients, using NeMo Guardrails to ensure data security and topic relevance.
Accelerated AI-driven research cycles by 15x on a HIPAA-regulated HPC cluster by implementing a parallelized software architecture with vLLM within an Agile development framework while utilizing Site Reliability Engineering techniques to employ information security methods to protect sensitive data.
Tools: Python, LangChain, LangGraph, PubMed Central API, PyTorch, vLLM, Bash

August 2024 - Present | Ann Arbor, Michigan

Suuchi

Machine Learning Engineering Intern

Deployed Predictive Modeling using Lightwood and Hugging Face models on Docker to develop 5+ proprietary ML Models.
Analyzed information using the internal database and integrated ML models into the SAAS platform services of ”Suuchi GRID”, resulting in a 27% increase in orders.
Tools: Python, MindsDB, Hugging Face, Lightwood, PyTorch, Apache Superset, Docker, PostgreSQL

May 2024 - November 2024 | Jersey City, New Jersey