Python + GenAI Intern

About the Role

Our engineering team is building LLM-powered features that real users rely on every day. As a Python + GenAI intern, you will work alongside senior engineers on live projects. You will design, build, and evaluate RAG pipelines and AI agents, and ship your work to production by the end of the internship.

What You'll Work On

• Build RAG pipelines: document ingestion, chunking, embeddings, vector search, and grounded answer generation.
• Develop LLM agents that use tools, call APIs, and complete multi-step tasks reliably.
• Write and iterate on prompts, and run structured experiments to improve output quality.
• Set up evaluation for LLM outputs: test sets, accuracy and hallucination checks, latency and cost tracking.
• Write clean, tested Python services (e.g., FastAPI) that expose AI features to other teams.
• Integrate with LLM providers and open-source models, and compare them on quality, speed, and cost.
• Document your work and present a demo of your project to the engineering team at the end of the internship.

Requirements & Tech Stack

• Strong Python: data structures, OOP, writing modular and readable code.
• Solid grasp of computer science fundamentals: algorithms, complexity, databases, and APIs.
• Working knowledge of how LLMs behave: tokens, context windows, prompting, temperature, and hallucinations.
• Hands-on experience calling at least one LLM API (OpenAI, Anthropic, Gemini or an open-source model).
• At least one AI or GenAI project (academic, personal, hackathon, or internship) you can walk through end to end.
• Comfort with Git and the command line.
• Clear written and spoken communication in English.

Good to Have

• Experience with LangChain, LlamaIndex, LangGraph or similar orchestration frameworks.
• Familiarity with vector databases such as FAISS, Chroma, Pinecone, Weaviate or pgvector.
• Exposure to agent patterns: tool calling, function calling, MCP, planning, and memory.
• Basics of ML and deep learning (PyTorch or TensorFlow, transformers, embeddings, fine-tuning).
• Experience with FastAPI or Flask, Docker, and any cloud platform (AWS, GCP or Azure).
• Kaggle rankings, open-source contributions, research papers, or hackathon wins.

Eligibility

• Final-year or pre-final-year students, or 2026 graduates, from Tier 1 institutes (IITs, NITs, IIITs, BITS and equivalent).
• B.Tech / B.E. / M.Tech / M.Sc / Dual Degree in Computer Science, IT, AI/ML, Data Science, Mathematics & Computing, ECE, or related fields.
• Minimum CGPA of 7.5 / 10 or equivalent.
• Available full-time for the entire 6-month period, with a college NOC if required.

What You'll Gain

• Ownership of a real GenAI feature, from design to production deployment.
• Weekly 1:1 mentorship from a senior engineer, plus regular code reviews.
• Access to LLM APIs and compute to experiment freely.
• Internship certificate and a letter of recommendation based on performance.
• Outstanding interns may be considered for future full-time opportunities.

Selection Process

• Resume and project shortlisting.
• Online assessment: Python coding plus a short GenAI fundamentals quiz (60 minutes).
• Take-home task.
• Technical interview: walkthrough of your take-home and past projects.
• Final discussion with the hiring manager.

To Apply: Send your resume to palak.choudhary@authbridge.com