Senior AI Engineer @ ThoughtFocus

About the Role

• Design, develop, and deploy multi-agent AI systems using open-source or enterprise-level frameworks.
• Translate complex business requirements into scalable agent-based AI architectures.
• Implement Generative AI and RAG pipelines, leveraging enterprise-grade tools such as LangChain, LlamaIndex, or similar.
• Architect and build modular and extensible agentic AI systems, using frameworks like LangGraph, CrewAI, AutoGen, etc.
• Collaborate with cross-functional teams (Product, Data, Engineering) to ship AI-powered features into production.
• Build APIs, microservices, or full-stack solutions (as needed) to support AI capabilities.
• Stay current on the latest advancements in LLMs, multi-agent coordination, and open-source AI tools.
• Ensure system reliability, scalability, and performance in a production-grade enterprise environment.

• Proficient in Python with strong software engineering fundamentals (OOP, design patterns, unit testing, CI/CD).
• Demonstrated experience building production-ready Generative AI applications (LLMs, RAG, chat-based tools).
• Hands-on knowledge of LangChain, LlamaIndex, or similar enterprise-grade GenAI libraries.
• Deep understanding of agent-based AI architectures and frameworks like LangGraph, CrewAI, AutoGen, etc.
• Experience with multi-agent orchestration, task decomposition, memory management, and reasoning loops.
• Familiarity with vector databases, embedding models, and prompt engineering best practices.
• Ability to take business requirements and build intelligent agentic systems with measurable results.
• Strong understanding of REST APIs, cloud platforms (AWS/GCP/Azure), and optionally DevOps practices.

• Experience with graph algorithms and graph-based reasoning systems.
• Familiarity with cognitive architectures or planning algorithms.
• Contributions to open-source AI projects or research publications.