Job Purpose

We are seeking a highly motivated and skilled AI Engineer to join our team and drive innovation in the rapid-evolving landscape of Generative AI. The ideal candidate will have deep hands-on expertise in RAG (Retrieval-Augmented Generation) pipelines and working familiarity with Frontier Models (e.g., GPT-4, Claude, LLaMA, etc.). Exposure to cutting-edge orchestration frameworks like CrewAI, LangGraph, Autogen, or OpenAI SDK is highly desirable.

You will work closely with product, data, and engineering teams to prototype, build, and scale AI-first solutions that deliver tangible business impact. Solid communication skills are key, as you’ll be working with cross-functional teams and occasionally interfacing with clients.

Responsibilities
Design and implement scalable RAG pipelines to enable contextual, high-quality responses using enterprise knowledge bases.
Evaluate and integrate Frontier LLMs /Open source LLM and APIs for specific tasks, ensuring optimal performance and efficiency.
Build autonomous agent workflows using tools like CrewAI, LangGraph, Autogen,



or OpenAI SDK.
Develop and optimize prompts, chains, and multi-agent systems.
Stay updated on the latest in the GenAI ecosystem and make recommendations for internal adoption.
Collaborate with stakeholders to understand use cases, define solution architectures, and iterate prototypes into production-ready systems.
Ensure responsible AI practices, including data privacy, model explainability, and
compliance.

Required Skills & Experience
6 to 7 years of overall industry experience with at least 1–2 years in Generative AI /LLM-focused projects.
Robust understanding of Frontier LLMs and their application across domains.
Hands-on experience in IDE’s such as Cursor
Hands-on experience building Retrieval-Augmented Generation systems using vector databases (like FAISS, Weaviate, or Pinecone).
Working knowledge of CrewAI, LangGraph, Autogen, or similar agent orchestration framewor

📌 Ai Engineer Bengaluru
🏢 Welldoc
📍 Bengaluru