LLM/GenAI Engineer | NLP, RAG, Explainability, MoE | PyTorch, FastAPI, LangChain | Open to GenAI Remote roles
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
explainable-agentic-rag
May 16, 2026 – Present
A portfolio project for building a reliable, explainable, evaluated Agentic RAG system with LangChain, LangGraph, Phoenix/OpenTelemetry tracing, and RAGAS-style evaluation
View Projectindic-research-agent
May 5, 2026 – Present
A public research assistant for Indic-language and India-focused work, built with Chainlit, LangGraph, LiteLLM, query-kit search, PostgreSQL persistence, and Redis caching without embedding or vector databases.
View Projectquery-kit
May 2, 2026 – Present
a small python cli installable via uv tool and uses httpx python3, and can be used by anyone to invoke for queries and get results
View Projectmcp-hands-on
April 11, 2026 – Present
A hands-on MCP server demonstrating all three primitives — Tools, Resources, and Prompt Templates — with calculator, weather, and notes features. Built with FastMCP Python SDK.
View Projectxai-rag
April 5, 2026 – Present
Explainable RAG — Production RAG with retrieval attribution, NLI faithfulness scoring, hybrid search + RRF, cross-encoder re-ranking, and RAGAS evaluation.
View Projectsafespeech-indic-hate-mitigation
February 6, 2026 – Present
SafeSpeech pipeline for hate intensity classification, explanation, and mitigation in Indic social media text
View Projecthealthcare_fraud_classification
March 14, 2024 – October 26, 2024
End-to-end healthcare fraud detection pipeline: merge claims + beneficiary + provider data, perform EDA/feature engineering, and benchmark ML models (RF, LightGBM, DT, SVM, ANN) with cross-validation.
View Projecttwitter_sentimental_analysis
April 9, 2019 – May 16, 2019
Sentiment Analysis is a term that you must have heard if you have been in the Tech field long enough. It is the process of predicting whether a piece of information (i.e. text, most commonly) indicates a positive, negative or neutral sentiment on the topic. In this project, I will go through making a Python program that analyzes the sentiment of tweets on a particular topic. The user will be able to input a keyword and get the sentiment on it based on the latest 100 tweets that contain the input keyword.
View Projectquiz
February 18, 2018 – January 21, 2022
It is a quiz web app created using Django and Bootstrap 4.
View ProjectCultural Fit Analysis
The candidate's projects show a strong interest in cutting-edge AI/ML topics, particularly in NLP and RAG systems, which aligns well with an innovative, research-oriented culture. The focus on Indic languages and social impact (hate mitigation) suggests a candidate who values meaningful contributions. However, the lack of team projects or professional experience makes it difficult to fully assess cultural fit in a collaborative work environment.
Soft Skills & Operational Fit
Insufficient data to assess soft skills and operational fit. The candidate's project descriptions indicate an ability to work on diverse technical challenges, but there is no information on collaboration, communication, or problem-solving in a team context.