Lead AI Engineer GenAI Agentic AI
Summary
Hands-on Lead AI Engineer who designs, builds, and maintains a production-oriented reference application using Python, LLM APIs, RAG pipelines, and agentic AI orchestration (OpenAI/Azure OpenAI/Claude, LangChain/LangGraph, vector databases like pgvector), while mentoring team members and defining the AI architecture, standards, and roadmap.
Job Summary
Databloom LLC is seeking an experienced, hands-on Lead AI Engineer to architect, develop, and maintain a production-oriented reference application using Generative AI, Retrieval-Augmented Generation (RAG), and Agentic AI technologies.
The Lead AI Engineer will own the reference project's technical implementation while mentoring a team of IT professionals working in company-provided development environments.
This is a combined hands-on development, technical leadership, and mentoring role.
Key Responsibilities
- Design the overall AI application architecture, technology stack, and technical roadmap.
- Personally develop and maintain a working reference application using Python, LLM APIs, RAG, and AI agent orchestration.
- Implement integrations with databases, vector search, REST APIs, and enterprise tools.
- Develop modular, reusable, well-documented code that members can use as a technical reference.
- Implement appropriate testing, evaluation, security, logging, and deployment practices.
Define expected outputs, technical acceptance criteria, and assignment completion guidelines.
- Provide sample code, configuration examples, and troubleshooting documentation.
- Guide members in independently implementing assigned modules within their provided development environments.
Required Technical Skills
- 5+ years of professional software engineering experience, with substantial hands-on experience building Generative AI applications.
- Strong Python programming, application architecture, and API development.
- Hands-on integration with OpenAI, Azure OpenAI, Claude, or comparable LLM APIs.
- Experience with LangChain, LangGraph, or comparable agent orchestration frameworks.
- Practical implementation of RAG pipelines, embeddings, hybrid search, reranking, and vector databases.
- Experience with pgvector, Azure AI Search, Databricks Vector Search, or comparable retrieval platforms.
- Agent tool calling, workflow state management, error handling, and context engineering.
- REST API integration, Git, Docker, cloud deployment, and CI/CD fundamentals.