AI Engineer with 2+ years in LLM, Generative AI, and multi-agent systems.
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 around 2 years of experience building production-ready LLM, Generative AI, Retrieval-Augmented Generation (RAG) and agentic systems across healthcare and enterprise domains. Designed end-to-end delivery of multi-agent clinical evaluation platform achieving 95% clinical accuracy with 45 minutes to 30-second physician review turnaround at 1,000+ candidates/day. Experienced in scalable RAG pipelines, LLM fine-tuning, async inference architecture, LangSmith observability, and cloud-deployed agentic workflows. Skilled in Python, LangGraph, LangChain, Hugging Face, FastAPI, Flask, vLLM, vector databases, Docker, AWS, and Azure.
Digital University Kerala, Trivandrum
Master of Science · Computer Science with specialization in data analytics
August 1, 2022 – June 30, 2024
Sacred Heart college, Ernakulam
Bachelor of Science · Physics
August 1, 2018 – June 30, 2021
Reizend Pvt Ltd India
AI Engineer
August 1, 2024 – Present
Thiruvananthapuram, Kerala, India
BzAnalytics Information Technology LLC
AI Intern
March 1, 2024 – June 1, 2024
Thiruvananthapuram, Kerala, India
AMAN.AI Phase 2 - Multi-Agent Clinical Evaluation Platform
August 1, 2024 – June 1, 2026
Architected specialist sub-agents for ECG, Spirometry, biomarkers, vision, and lab reports with tool calling, consensus routing, and Qdrant-backed guideline retrieval; serving 1,000+ candidates/day on async AWS Lambda. Deployed RAGAS evaluation loop + LangSmith tracing for continuous quality monitoring, hallucination scoring, and retrieval diagnostics in production.
Cardiovascular Disease Prediction System
March 1, 2024 – June 1, 2024
Developed and deployed a machine learning pipeline for binary classification of cardiovascular disease risk using structured clinical and demographic datasets. Implemented end-to-end preprocessing workflows including missing value imputation, binary encoding, feature engineering, and feature scaling to improve model robustness and predictive performance. Trained and optimized an XGBoost-based classification model for disease prediction, leveraging feature importance analysis and hyperparameter tuning for improved classification accuracy. Built RESTful FastAPI inference endpoints and deployed the prediction service on AWS EC2, enabling scalable real-time disease risk assessment through API-based inference workflows.
Agentic API Testing Automation System
March 1, 2024 – June 1, 2024
Developed an agentic API testing automation system using LangGraph and GPT-4.1-mini that generates dynamic Pytest test suites from OpenAPI schemas and structured test cases for automated endpoint validation. Built automated workflows for parsing API specifications, generating executable test scenarios, and validating endpoint behavior against expected outputs through LLM-driven test orchestration.
AMAN.AI Phase 1 - Medical Document Extraction & VLM Evaluation Pipeline
March 1, 2024 – June 1, 2024
Built and evaluated multimodal medical document extraction pipelines using Vision-Language Models including Qwen2.5-7B, Llama 3.2 Vision, InternVL, and Mistral for structured clinical information extraction from complex medical PDFs. Benchmarked multiple VLM architectures across medical document understanding tasks including table extraction, report parsing, OCR robustness, and structured JSON generation to identify optimal accuracy-latency tradeoffs. Deployed high-throughput inference services on AWS EC2 using vLLM with optimized GPU serving workflows, enabling scalable low-latency processing for medical document extraction workloads. Designed structured post-processing and normalization workflows to convert extracted multimodal outputs into standardized JSON schemas for downstream agentic clinical evaluation systems.
Complete Data Science, Machine Learning, DL,NLP Bootcamp
Udemy
January 1, 2025 – Present
Cultural Fit Analysis
The candidate's project portfolio demonstrates a strong alignment with an AI Engineer role, particularly in applied AI, LLM, and RAG domains. The diversity of projects, from clinical evaluation platforms to API testing automation, shows adaptability and a broad interest in AI applications. The experience in both a startup (Reizend) and an internship (BzAnalytics) suggests an ability to thrive in dynamic environments. The specialization in data analytics during their Master's further reinforces a strong foundation for data-driven roles.
Soft Skills & Operational Fit
The candidate's project descriptions indicate a strong problem-solving aptitude, evidenced by optimizing complex systems for performance and accuracy. The focus on production deployment and continuous monitoring (RAGAS, LangSmith) suggests a practical, results-oriented approach. The ability to work with clinical staff for validation implies good collaboration and communication skills in a professional setting.