Full Stack & AI Engineering Intern

Nuvama's Quant Engineering team builds internal platforms that power quantitative research and systematic trading. We are expanding our investment in AI-driven tooling and are looking for engineering interns who can contribute across the full stack — from production APIs and React interfaces to LLM integration and fine-tuning pipelines.

Duration: 6 months

What You'll Work On

• Full stack product development: building and iterating on internal research and analytics platforms using React, TypeScript, and Python (FastAPI). Includes dashboards, data visualisation components, real-time data feeds, and workflow UIs.
• LLM integration and agent development: integrating large language models into internal tooling via API (function-calling, multi-turn conversations, tool use). Building agent backends that connect LLMs to internal data sources and services.
• Fine-tuning pipelines: constructing supervised fine-tuning (SFT) datasets from internal corpora and running fine-tuning jobs using LoRA/QLoRA on open-source base models (Llama 3, Mistral, Phi-3). Evaluating outputs on domain-specific benchmarks.
• Retrieval-Augmented Generation (RAG): building and evaluating RAG pipelines over internal document and data stores using vector search. Experimenting with chunking strategies, embedding models, and retrieval quality metrics.
• Backend services and APIs: building REST and WebSocket APIs, async task workers, and data ingestion pipelines that serve the…

Skills

• LLMs
• React.js
• TypeScript
• Python
• FastAPI