AI Implementation Engineer

Tasks and deliverables

• Design and build AI agents and LLM-powered workflows.
• Implement RAG systems using vector databases, embeddings, chunking strategies, and retrieval optimization.
• Work with frameworks such as LangChain, LangGraph, Langsmith, Langfuse, LlamaIndex, or similar tools.
• Integrate LLMs with APIs, internal systems, databases, and external services.
• Evaluate model outputs, improve prompt strategies, and support testing and observability.
• Collaborate with product and engineering teams to turn AI use cases into reliable software.

Required Experience

• Strong software engineering experience, preferably with Python and modern backend systems.
• Hands-on experience designing and building RAG pipelines, MCP Servers, Single or Multi agent Systems and/or LLM-based applications.
• Experience with LangGraph, LangChain, LlamaIndex, Semantic Kernel, or similar frameworks.
• Understanding of embeddings, vector databases, retrieval strategies, and prompt engineering.
• Experience integrating LLMs with tools, APIs, and structured workflows.
• Ability to evaluate AI system quality, latency, cost, and reliability.
• Comfortable working in fast-moving, ambiguous environments.