Design, build, and maintain data pipelines and integrations leveraging PostgreSQL Server and Snowflake for downstream AI and analytics use cases.
Own the end-to-end LLM application lifecycle from prompt engineering and retrieval workflow design through evaluation, observability, security, and performance tuning.
Design and implement a production-grade, enterprise-class multi-agent framework that is reliable, scalable, and maintainable in live environments.
Architect and deploy multi-agent, enterprise-class AI/agentic solutions on the Azure platform, aligning with Azure-native services and best practices.
Collaborate with cross-functional stakeholders to translate business requirements into robust, enterprise-class, production-ready AI system designs.
Ensure multi-agent LLM systems meet performance, security, and observability standards before and after deployment.
Communicate technical decisions and trade-offs clearly to both technical and non-technical partners.
Roles & Responsibilities
Demonstrated, hands-on experience designing, building, and deploying a production-grade, enterprise-class multi-agent framework in real-world systems.
Strong, hands-on experience with PostgreSQL Server and Snowflake, including schema design, query optimization, and data integration.
Solid understanding of the LLM application lifecycle: prompt engineering, retrieval-augmented workflows, evaluation methodologies, observability tooling, security considerations, and performance optimization.
Required hands-on experience with the Azure platform for building and deploying multi-agent, enterprise-class AI/agentic solutions.
Strong grasp of multi-agent architecture patterns (orchestration, coordination, agent-to-agent communication) at enterprise scale.
Ability to take ambiguous requirements through to delivered, production-ready, enterprise-class outcomes with minimal hand-holding.
Strong communication skills, with the ability to explain complex multi-agent system behavior to varied audiences.