Lead AI Engineer

• Own end-to-end technical design and delivery of GenAI/agentic systems for internal or external applications

• Architect multi-agent workflows using tools like LangChain, A2A protocols, and custom orchestration frameworks

• Guide the design and tuning of prompt architectures, context strategies (e.g., with MCP), and hybrid RAG pipelines

• Integrate AI services into enterprise platforms such as Azure Foundry, Databricks, and core business systems

• Lead engineering pods, mentor engineers across levels, and drive technical alignment across product and platform teams

• Push the boundaries of performance, latency, and accuracy through research-backed optimization

• Define reusable templates, shared components, and internal GenAI SDKs

• Enforce standards around ethical AI use, context control, prompt security, and hallucination mitigation

Required Skills:

• 7+ years of experience in AI/ML/GenAI solutioning, with 3+ years in technical leadership

• Deep proficiency in Python 3 with strong command over openai, pydantic, transformers, faiss, and langchain

• Demonstrated experience in deploying scalable GenAI solutions with cloud-native design

• Strong working knowledge of Azure cloud services, GitHub workflows, and CI/CD best practices

• Experience in vector store optimization, token-level control, and prompt performance management.

Nice-to-have skills:

• Hands-on leadership in projects involving MCP, A2A orchestration, or custom agentic services

• Contributor to open-source GenAI tooling or frameworks

• Familiarity with prompt observability and compliance tooling

• Experience in conducting code reviews, architecture walkthroughs, and internal capability building

• Thought leadership via internal brown-bags, hackathons, or community talks