Lead Generative

Description:

Responsibilities
 

• Define, design, and deliver robust, scalable, and secure GenAI and multi-agent architectures (RAG, tool calling, event-driven pipelines).
• Lead the development and deployment of Python back-end services, integrating LLMs and sophisticated multi-agent frameworks into production environments.
• Establish and govern LLMOps practices, including model-tuning data pipelines, benchmarking, observability, drift monitoring, and safe rollout strategies.
• Serve as a technical leader, mentoring engineering pods and partnering with product, security, and legal teams to ensure compliant, high-impact solutions.
   

Qualifications

13+ years in software/technology with significant, proven experience deploying Generative AI systems to production at scale.

Expertise in designing and delivering modular multi-agent systems with dynamic tool integration and context-aware reasoning, leveraging frameworks like LangChain, AutoGen, or Semantic Kernel.

Strong Python skills for backend service development, and experience with modern data processing (e.g., Spark).

Deep, hands-on knowledge of cloud GenAI services (Azure preferred: Azure OpenAI, AKS) and vector databases.