onsite
AI/ML Engineer - W2S Solutions
ML Engineer
Seasoned AI/ML Engineer with 5‑10 years experience designing, building, and deploying enterprise‑grade generative AI solutions, leveraging Python, LLMs, LangChain, RAG pipelines, vector databases, and OpenAI APIs.
About the role
Key Responsibilities
- Design, develop, and deploy scalable AI‑powered applications using Python and enterprise‑grade LLMs.
- Build and maintain generative AI solutions, including Retrieval‑Augmented Generation pipelines with vector databases and semantic search.
- Create intelligent workflows with LangChain, LangGraph, and LlamaIndex, integrating Model Context Protocol for tool calling and multi‑agent orchestration.
- Integrate, fine‑tune, and optimize OpenAI and other LLM models for diverse business use cases.
- Collaborate with cross‑functional teams to ensure AI solutions meet performance, security, and scalability requirements.
Requirements
- 5–10 years of professional experience in AI/ML engineering, with a strong focus on generative AI.
- Proficiency in Python and extensive hands‑on experience with large language models (e.g., OpenAI, Anthropic, LLaMA).
- Deep knowledge of LangChain, LangGraph, LlamaIndex, and Retrieval‑Augmented Generation techniques.
- Experience building and querying vector databases for semantic search (e.g., Pinecone, Weaviate, Milvus).
- Ability to design multi‑agent systems using Model Context Protocol or similar orchestration frameworks.