Where I've worked and studied, and what I work with.
Cognizant, London
AI Engineer · February 2026 – Present
- Sole AI Engineer on an agentic data-discovery tool on Azure for a UK public sector client, letting analysts self-serve queries across 200+ enterprise datasets in plain English.
- Cut dataset discovery from days of back and forth with the statistics team down to minutes.
- Designed the orchestration layer in which a coordinating LLM decomposes each query, routes sub-tasks to specialised LLM calls or Python functions, then consolidates the results.
- Shipped it as an Azure Function with response streaming, graceful failure handling and managed-identity auth, integrated into the client's existing infrastructure.
- Embedded with analyst end users, translating ambiguous business-language requests into concrete technical requirements through rapid demo-and-feedback cycles.
Stack: Python, Azure OpenAI, FastAPI, Azure Functions, agentic orchestration
ZS Associates, Bangalore
Advanced Data Science Associate · July 2022 – August 2024
- Built and productionised LLM systems over unstructured healthcare and insurance data.
- Built an LLM chatbot answering insurance agents' plain-English questions, from single-policy lookups to geographic aggregates, by compiling each into a dynamically generated Python retrieval pipeline. Increased the client calls each agent could handle by 25%.
- Engineered the data-acquisition backend powering the chatbot: a scraping-and-parsing pipeline that structured 3,000+ unstructured insurance policies into a queryable knowledge base.
- Architected an LLM-driven insight-mining pipeline over 100K+ unstructured healthcare documents, combining clustering with RAG-based entity extraction across 10K+ physician notes to cut retrieval latency by 40% and inform safety reviews and marketing strategy.
Stack: Python, LangChain, Haystack, PyTorch, RAG, AWS
Microsoft IDC, Hyderabad
Software Engineer Intern · May 2021 – July 2021
- Part of the Microsoft Search, Assistance and Intelligence team.
- Developed voice assistant features for Microsoft Search, improving enterprise search accessibility and daily user engagement.
- Built RESTful APIs, frontend components and YAML conversational datasets alongside product and design teams, improving intent recognition and accelerating delivery of production features.
Stack: TypeScript, Express, Node.js, YAML, Azure
The University of Sheffield
MSc Computer Science with Speech and Language Processing, Distinction · September 2024 – November 2025
Dissertation: Hallucination Span Detection in Large Language Models. Read the dissertation.
BITS Pilani, Goa Campus
B.E. Electronics and Instrumentation · August 2018 – May 2022
Undergraduate research: Transformer-based Models for Supervised Monocular Depth Estimation, published at ICICCSP 2022. Read the paper.