About this role

You build LLM-powered features and prompt workflows that make RemoteStar smarter, across candidate matching, screening, and internal automation. This is the fastest-growing track in tech, and we keep it genuinely open to freshers who can show real, hands-on work with models. You will move quick, measure carefully, and ship AI features into a live product.

Key responsibilities

- Build and ship product features powered by large language models.

- Design, test, and iterate on prompts and multi-step prompt workflows.

- Integrate model APIs and Retrieval-Augmented Generation (RAG) into real products.

- Build evaluations to measure output quality and catch regressions before users do.

- Prepare and clean data, and debug model behaviour when outputs go wrong.

- Keep pace with a field that changes week to week, and bring the best of it back to the team.

Required qualifications





- Python and solid general programming fundamentals.

- Hands-on exposure to LLM APIs (Anthropic, OpenAI, or similar), LangChain, or RAG.

- A GitHub project, demo, or write-up showing something you actually built with models.

- Strong curiosity, self-direction, and product judgement.

Preferred qualifications

- Vector databases (pgvector, Pinecone, Weaviate) and embeddings.

- Experience with evals, guardrails, or agent frameworks.

- Fine-tuning, structured outputs, or tool-use / function-calling experience.

Internship Duration: 6 Months Stipend: ₹15,000 – ₹25,000 per month Pre-Placement Offer (PPO): Eligible candidates may be offered a full-time position based on their performance during the internship, subject to the company's evaluation criteria.

📌 Generative AI Specialist (India)
🏢 Remotestar
📍 India