Create your free profile

About

Senior LLM Engineer with 5+ years of hands-on experience building, fine-tuning, and shipping production-grade LLMs and agentic AI systems. Core expertise spans the full LLM lifecycle — pre-training data pipelines, SFT/RLHF post-training, RAG architecture, multi-agent orchestration, and systematic prompt engineering.

Experience3

  1. LLM Pre/Post-Training Specialist & AI Evaluator (Freelance)

    Jan 2020 — Present

    Upwork — Productive Playhouse / Large Programs

    Curated and structured large-scale pre-training corpora for language models, maintaining 98%+ annotation accuracy across 30k+ examples. Delivered SFT datasets and preference pairs for LLM fine-tuning projects. Evaluated Hindi-language AI responses, achieving a 100% Job Success Score.

  2. LLM Pre/Post-Training Specialist & AI Evaluator (Freelance)

    Jan 2020 — Present

    Upwork — Productive Playhouse / Large Programs

    Curated and structured large-scale pre-training corpora for language models, maintaining 98%+ annotation accuracy across 30k+ examples. Delivered SFT datasets and preference pairs for LLM fine-tuning projects. Evaluated Hindi-language AI responses, achieving a 100% Job Success Score.

  3. Senior AI Data Trainer & Annotator

    Jun 2018 — Dec 2020

    RWS Community / Outlier.ai / Welocalize / Sigma AI

    Annotated over 50,000 samples with 98%+ accuracy and led a sub-team of 6 annotators. Developed RLHF workflows for conversational AI and performed various NLP tasks including sentiment analysis and multi-turn prompt evaluation.

Projects7

  • Agentic RAG System with LangGraph + RAGFlow

    Built a stateful multi-agent RAG system using LangGraph for agent orchestration and RAGFlow for document ingestion and retrieval, achieving sub-400ms E2E latency and <4% hallucination rate.

    • Python
    • LangGraph
    • RAGFlow
    • LangChain
    • Pinecone
    • FastAPI
    • Docker
    • AWS EKS

  • LLM Pre-Training Data Pipeline & SFT Fine-Tuning

    Designed an end-to-end LLM pre-training data pipeline for a 7B-param domain LLM, followed by SFT using LoRA on SageMaker, reducing perplexity by 18% and hallucination rate by 42%.

    • Python
    • Hugging Face
    • LoRA/PEFT
    • AWS SageMaker
    • DPO
    • Reward Modelling
    • RLHF

  • Multi-Agent LLM Orchestration Platform

    Engineered a multi-agent framework using LangGraph stateful graphs and persistent Redis memory, achieving a 55% reduction in task completion time.

    • Python
    • LangGraph
    • LangChain Agents
    • OpenAI Function Calling
    • FastAPI
    • Redis
    • Docker
    • Kubernetes

  • Computer Vision Defect Detection Pipeline (Deep Learning)

    Trained and deployed a YOLOv8-based defect detection model for industrial quality control, achieving 94.3% [email protected] and deployed as a real-time FastAPI microservice.

    • Python
    • PyTorch
    • YOLOv8
    • OpenCV
    • AWS SageMaker
    • Docker
    • FastAPI

  • Automated LLM Evaluation & CI/CD Quality Gate

    Created a real-time evaluation dashboard tracking hallucination rate and answer relevancy, integrated with GitHub Actions CI/CD to cut regression detection time from days to minutes.

    • Python
    • DeepEval
    • Ragas
    • Streamlit
    • PostgreSQL
    • GitHub Actions
    • MLflow

  • Decibench — Voice Agent Benchmarking Framework

    Developed an open-source benchmarking framework for voice AI agents, supporting automated multi-turn conversation simulation and latency profiling.

    • Python
    • FastAPI
    • WebSockets
    • Whisper
    • LangChain
    • PostgreSQL
    • Docker

  • NearestDoctor — AI-Powered Healthcare Search

    Built a full-stack healthcare discovery platform with LLM-powered symptom-to-specialist matching and real-time doctor availability, achieving 99.5% uptime.

    • Next.js
    • React
    • Supabase
    • LangChain
    • OpenAI API
    • Vercel
    • TailwindCSS

Education1

  • B.Tech in Computer Science & Engineering

    2016 — 2020

    Punjab Engineering College, Chandigarh