Skip to content
View nikhilreddy00's full-sized avatar
πŸ’Ό
Open to AI/ML Engineer and Data Science Analyst roles
πŸ’Ό
Open to AI/ML Engineer and Data Science Analyst roles

Highlights

  • Pro

Block or report nikhilreddy00

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
nikhilreddy00/README.md

Typing SVG

LinkedIn Portfolio Email Profile Views


Hey there! πŸ‘‹

I'm Nikhil β€” an ML Engineer who builds AI systems that work in production, not just in notebooks.

Over 3+ years, I've intentionally progressed from data analysis β†’ NLP/ML modeling β†’ full-stack ML engineering across healthcare and e-commerce. That path was deliberate β€” I wanted to understand not just how models learn, but how they survive in the real world with messy data, latency constraints, and stakeholders who care about outcomes, not architectures.

Currently: Building RAG pipelines over 15K+ clinical records, fine-tuning BERT & Llama via LoRA, and deploying containerized inference endpoints on AWS SageMaker at GWU's Milken Institute School of Public Health.

Previously: Shipped semantic search systems across census datasets, built LangGraph-powered feature engineering agents, deployed demand forecasting models, and built analytics dashboards adopted by 10+ stakeholders.

Completing my MS in Data Analytics at George Washington University (May 2026).


πŸ”§ Tech Stack

Languages & Core

Python SQL PySpark R Bash

ML & Deep Learning

PyTorch TensorFlow scikit--learn XGBoost HuggingFace BERT

GenAI & LLM Tooling

LangChain LangGraph OpenAI Pinecone ChromaDB FAISS RAG LoRA/QLoRA

MLOps & Cloud

Docker Kubernetes AWS SageMaker Azure MLflow FastAPI Airflow CI/CD

Data & Databases

PostgreSQL MongoDB Snowflake BigQuery Spark Databricks dbt

Analytics & Visualization

Power BI Tableau Streamlit Pandas NumPy Matplotlib


πŸ’Ό Career Journey

 2022─2024                    2024                         2025─Present
β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”     β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚  Data Scienceβ”‚     β”‚  Data Scientist     β”‚     β”‚  ML Engineer            β”‚
β”‚  Analyst     │────▢│  (NLP/ML)           │────▢│                         β”‚
β”‚  Cogno AI    β”‚     β”‚  DSSD               β”‚     β”‚  Milken Institute, GWU  β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜     β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜
 β€’ Analytics &        β€’ FAISS semantic search    β€’ RAG pipelines (15K+ docs)
   dashboards         β€’ LangGraph agents         β€’ LLM fine-tuning (LoRA)
 β€’ RAG + Pinecone     β€’ PySpark + Databricks     β€’ AWS SageMaker deployment
 β€’ XGBoost forecasts  β€’ Azure OpenAI dashboards  β€’ MLflow + CI/CD pipelines
 β€’ MLOps (MLflow)     β€’ NLP feature engineering  β€’ Containerized inference

πŸ“Š GitHub Stats


🎯 What I'm Working On

  • πŸ”¬ Building agentic RAG systems with LangGraph for healthcare research
  • πŸ› οΈ Shipping containerized ML endpoints (FastAPI + Docker + SageMaker)
  • πŸ“ Fine-tuning open-source LLMs (Llama, Mistral) via LoRA/QLoRA
  • πŸŽ“ Completing MS in Data Analytics @ George Washington University (May 2026)
  • πŸ“¦ Migrating production projects to public repos β€” stay tuned

πŸ“« Let's Connect

I'm actively looking for ML Engineer, AI Engineer, and Applied Scientist roles. If you're building something interesting with LLMs, RAG, or production ML β€” let's talk.

LinkedIn Portfolio


Pinned Loading

  1. sec-finance-rag sec-finance-rag Public

    Production RAG chatbot over 25,000+ SEC EDGAR filings (S&P 500) β€” Claude Β· BGE Β· Hybrid BM25+Dense Β· Cohere Rerank Β· FastAPI Β· Streamlit

    Python

  2. Metadata-Aware-Rag Metadata-Aware-Rag Public

    Production-ready Metadata-Aware RAG system for SEC EDGAR filings with Self-Querying & Multi-Query Retrieval, backed by Qdrant vector DB and Groq LLM.

    HTML

  3. MedSignal-API MedSignal-API Public

    Real-time drug safety intelligence API. Hybrid RAG combining live openFDA adverse events, PubMed literature, and a FAISS biomedical knowledge base β€” synthesized by Llama 3.3-70B via Groq.

    Python

  4. pharma-agent pharma-agent Public

    Autonomous drug safety intelligence system using agentic RAG β€” answers complex pharmacovigilance questions by cross-referencing FDA labels, PubMed, and clinical guidelines in under 60 seconds.

    Python