Forward Deployed Engineer who build and ship AI‑driven products end to end – from problem framing to production deployment – with a strong focus on Generative AI, LLMs and scalable backend systems. My work sits at the intersection of AI engineering and product development: I design RAG pipelines, agentic workflows and LLM‑powered APIs that solve real business problems, not just lab demos. In recent projects, I’ve architected an RFP insight engine and high‑throughput AI parsers, and built a GenAI platform that matches health insurance policies to medical cases using AWS Textract, Lambda, Bedrock and GPT‑4‑class models. Today, I’m interested in roles such as Generative AI / LLM Engineer, AI Engineer, AI Product Engineer and AI‑first Backend Engineer, where I can: – Design and implement RAG and agentic pipelines for real‑world use cases – Build and optimize Python/FastAPI services that integrate LLMs into products – Deploy AI systems on cloud (AWS) and manage performance, reliability and cost – Partner with product and business teams to take AI features from idea to launch. Core technical focus: – Generative AI & LLMs: RAG, prompt engineering, agent workflows, evaluation and fine‑tuning – Engineering & Deployment: Python, FastAPI, REST APIs, local LLMs (Ollama), edge / cloud deployments I thrive in teams that ship production AI – where we measure impact, close the loop between users and systems, and keep improving models and infrastructure over time. Open to opportunities in Hyderabad and remote roles where LLMs and AI products are at the core of the roadmap.
Product Development Associate
TekFriday Processing Solutions Pvt Ltd
- Increased support-team throughput by ~150% (trial-run estimate, tickets processed per associate) by designing and building a custom agentic email-triage system that classifies, routes, and drafts responses to customer emails.
- Reduced hallucinations by 80% versus baseline prompts by building a custom evaluation set of 300+ evaluations (HELM-based definitions, Pydantic validation, LLM-as-judge) and iterating on prompts against it.
- Improved accuracy, latency, and reliability by designing the workflow around prompt chaining, routing, orchestrator, and evaluator patterns, then optimizing it end to end.
- Grounded responses by combining RAG with LLM integrations into internal tools and APIs to enable autonomous task execution.
- Delivered the system to internal users by containerizing it with Docker and deploying it as an API service on AWS EC2, partnering with product and engineering teams and presenting progress to technical and non-technical stakeholders.
Junior Software Developer
eServe Consulting
- Automated business workflows with Apex classes and triggers, with governor-limit-safe SOQL optimization.
- Built responsive front-end interfaces with Lightning Web Components (LWC).
- Delivered scalable CRM features with product teams by integrating Salesforce with external services through REST APIs.
FinBot, RAG enterprise chatbot
Built department-based RBAC routing over a RAG pipeline. Completed a 26-finding security and architecture review and wrote a 6-week remediation roadmap covering Indian PII detection (PAN, Aadhaar, UPI) and DPDPA/RBI compliance.
GenAI Health Insurance Policy Matcher
Matched health insurance policies to medical cases with a GenAI pipeline on AWS Textract, Lambda, Bedrock, and GPT-4-class models.
RFP Insight Engine
Extracted and structured RFP insights with a high-throughput AI parsing engine.
M.S., Artificial Intelligence (in progress)
Woolf University
Postgraduate Certificate, Data Science and Machine Learning
MITx
M.Sc., Management Engineering (joint program)
Maastricht University (Management) | RWTH Aachen University (Engineering)
B.E., Production Engineering
Chaitanya Bharathi Institute of Technology
AWS Certified Cloud Practitioner
Amazon Web Services
Agentic Thinking 101
AI Programming with Python
Attendee · Oct 24, 2026