AI Engineer with 2+ years in Agentic AI Systems, LLM Engineering, and RAG Pipelines.
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 Engineer with 2+ years of experience in Agentic AI Systems, LLM Engineering, and RAG Pipelines. Expertise in designing end-to-end agent flows, memory & context engineering, and MCP server integrations using LangGraph, LangChain, and LangMem. Proficient in building production-grade agentic workflows, tool integrations, and connector frameworks using FastAPI, Docker, and AWS. Strong background in agent reliability, incident response, and human-in-the-loop systems.
Veer Surendra Sai University of Technology
Bachelor of Technology · Information Technology
December 1, 2020 – June 1, 2024
Fynd
AI Engineer
June 1, 2025 – Present
Mumbai, Maharashtra, India
Neophyte Ambient Intelligence
Product Engineer
July 1, 2024 – June 1, 2025
Navi Mumbai, Maharashtra, India
Neophyte Ambient Intelligence
Machine Learning Engineer Intern
December 1, 2023 – June 1, 2024
Navi Mumbai, Maharashtra, India
FastDoc-RAG
February 1, 2026 – June 30, 2026
Architected FastDoc-RAG, a Python document parsing library with multi-modal RAG pipeline—PDF parsing, semantic chunking, FAISS vector storage, and GPT-40 querying with image/table retrieval processing 11-page research papers in under 30 seconds with 10x faster parsing than Unstructured. Delivered 4 extraction strategies (fast, hi_res, OCR, auto) using DocLayout-YOLO (YOLOv10) for ML-based document layout detection with structured outputs, coordinate-space conversion, and custom borderless table extraction via x/y position clustering—maintaining comparable accuracy on text-heavy documents. Developed lightweight RAG-ready document parser (50MB vs 2GB+ install) with zero external service dependencies and supporting 15+ element types, multi-column layouts, and paragraph merging with optimized cost and latency for production grade document intelligence pipelines.
Autonomous PR Reviewer
May 1, 2025 – June 1, 2025
Integrated an LLM-powered autonomous PR review system using LangGraph, LangChain, and GPT-40 with end-to-end agent flow design including function calling, structured outputs, state management, retries, and human-in-the-loop approval flows with guardrails and fallback mechanisms via FastAPI with zero manual intervention. Crafted GitHub API connector and OAuth integration enabling the agent to autonomously fetch PR diffs, post review comments, and trigger merge actions with agent evaluation framework measuring precision, recall, and latency across prompt versions with safe rollback on performance regression.
Cultural Fit Analysis
The candidate's project diversity, ranging from autonomous PR review to retail/FMCG process automation and document parsing, indicates adaptability and a broad interest in applying AI solutions across different domains. Their experience in both product engineering and machine learning engineering roles, coupled with a strong academic background, suggests a well-rounded individual capable of contributing to various aspects of an AI team. The focus on production-grade systems and performance benchmarking aligns with a results-oriented culture.
Soft Skills & Operational Fit
The candidate demonstrates strong problem-solving skills through architecting complex AI systems and optimizing performance. Their experience with human-in-the-loop systems and agent evaluation frameworks suggests an operational mindset focused on reliability and continuous improvement. The project descriptions indicate a proactive and ownership-driven approach to development.