AI Engineer with 2+ years in LLM Systems & GenAI APIs
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
AI/ML Engineer with 3+ years of experience building production-grade LLM systems, RAG pipelines, and agentic AI workflows. Proven track record shipping low-latency GenAI APIs (FastAPI) serving 10K+ daily requests, fine-tuning large language models with QLoRA, and engineering NLP automation pipelines at scale. Hands-on with the full LLM stack from retrieval and ranking to generation and deployment. Seeking AI Engineer / ML Engineer / GenAI Developer roles.
Techno India University
B.Tech · Computer Science & Engineering (AI Specialisation)
November 1, 2021 – August 1, 2025
YUGA AI
AI & ML Engineer
December 1, 2025 – Present
India
New Gen Leads USA
Freelance AI Developer
January 1, 2023 – February 1, 2025
United States
CURA Retrieval-Augmented Medical QA System
June 25, 2026 – Present
Designed a RAG-based medical question-answering system with grounded, source-cited responses to reduce hallucination in high-stakes clinical queries.
ALADDINGO GenAI Travel Planning System
June 25, 2026 – Present
Developed a generative AI travel planning assistant as a capstone thesis project, integrating LLM reasoning with structured itinerary generation.
Auto-Researcher Multi-Agent Academic Review System
November 1, 2025 – December 1, 2025
Built a graph-based 3-agent LLM pipeline (LangChain + LangGraph) to automate academic literature review across 500+ papers, reducing manual review time significantly. Integrated academic search, PDF parsing, and citation-grounded summarisation, 1,000+ documents end-to-end with traceable research outputs. Implemented real-time agent streaming with a live research dashboard, reducing workflow latency by 40%.
AutoLLM Forge LLM Fine-Tuning Platform
September 1, 2025 – October 1, 2025
Built a QLoRA fine-tuning system for 2Bto70B parameter models, achieving 75% VRAM reduction and 30% training efficiency improvement using PyTorch and FastAPI. Developed a FastAPI + Next.js platform supporting 1,000+ HuggingFace models with automated inference pipelines and real-time training monitoring via WebSockets.
Machine Learning I
Columbia University / edX
January 1, 2025 – Present
CS50AI: Introduction to Artificial Intelligence with Python
HarvardX
January 1, 2025 – Present
Cultural Fit Analysis
The candidate's academic projects demonstrate a strong interest and initiative in cutting-edge AI research and development, particularly in GenAI and LLMs. Their experience as a Freelance AI Developer shows adaptability and the ability to deliver solutions across the full AI lifecycle. The current role at YUGA AI, focusing on production RAG systems, aligns well with a fast-paced, innovative AI engineering culture. The breadth of skills and diverse project types (medical QA, travel planning, academic review, fine-tuning platforms) indicate a versatile and curious individual who can contribute to various aspects of an AI team.
Soft Skills & Operational Fit
The candidate's project descriptions and experience highlight strong problem-solving skills, particularly in optimizing performance (latency reduction, VRAM reduction) and building end-to-end AI solutions independently. Their work on multi-agent systems and collaborative prompt engineering indicates an ability to work effectively in complex, team-oriented environments. The focus on real-time systems and production deployment suggests a practical, results-oriented approach.