Company Description
Cobay is building an all-in-one platform for e-commerce and D2C brands. We combine SaaS applications with AI-powered solutions to give online businesses everything they need to operate, scale, and grow—all in one place.
We're a fast-moving team solving real problems for e-commerce businesses, and we're looking for our next AI Engineer to help shape what we build.
Role Description
This is a full-time on-site role, located in Coimbatore. As an AI Engineer Intern at Cobay, you will help design and ship AI-powered features on top of our existing products, working across backend services, simple UIs, and LLM/RAG workflows. You'll collaborate with engineers and product owners to turn real business use-cases into small, production-ready AI tools, from integrating model APIs and retrieval pipelines to wiring them into our internal and customer-facing applications.
Qualifications
- Final-year or recent graduate in Computer Science / IT / AI / Data Science or related field, with solid programming fundamentals.
- Strong skills in Python plus working knowledge of JavaScript/TypeScript or any modern web stack.
- Understanding of LLM and RAG basics: embeddings, vector stores, retrieval, context window limits, and prompt design.
- Hands‑on experience (projects / internships / hackathons) building at least one LLM-based application such as a chatbot, Q&A bot, or AI assistant.
- Familiarity with one or more orchestration frameworks like LangChain, LlamaIndex, or similar tooling is highly preferred.
- Exposure to vector databases / search systems (FAISS, Chroma, Pinecone, Elasticsearch-vector, etc.).
- Ability to work with REST APIs, JSON, Git, and basic cloud or deployment workflows (any provider).
- Any prior work with AI agents, workflow builders, or automation around LLMs.
Key responsibilities
- Design and implement end‑to‑end AI-driven features such as smart assistants, intelligent search, and workflow automation for our existing platforms.
- Build and refine RAG-style pipelines: document ingestion, chunking, embeddings, vector search, and context assembly to provide accurate, contextual responses from domain data.
- Integrate LLM and GenAI APIs into backend services and microservices, exposing them via clean, well-documented REST endpoints.
- Work with the full stack team to connect these services to simple, usable UIs (dashboards, chat interfaces, internal tools) and ensure smooth user experience.
- Monitor behaviour of AI features, log edge cases, and iterate on prompts, retrieval logic, and guardrails to improve reliability.
- Collaborate with product and business stakeholders to understand use‑cases and translate them into small, shippable AI features.
