The AI/ML Engineer – Agentic is a senior individual contributor responsible for designing, building, and operating a production-grade agentic orchestration platform, including multi-agent workflows and MCP server–based tool infrastructure. The role focuses on enterprise-scale LLM integration, shared retrieval and memory services, and high-performance backend systems that power agent execution. This position owns reliability, observability, and cloud-native operations for non-deterministic agentic systems in production.

Design, build, and own a production-grade agentic orchestration platform, implementing scalable multi-agent workflows using frameworks such as LangGraph or equivalent.

Architect, develop, and operate the MCP server infrastructure, including inter-agent communication, tool/server registries, domain isolation, versioning, and lifecycle management.

Integrate and operate LLM services at enterprise scale, supporting streaming, structured outputs, tool/function calling, and robust error handling across agent workflows.

Build and maintain retrieval and memory services for agentic systems, including RAG pipelines, OpenSearch-backed vector stores, hybrid search, and relevance optimization.

Develop and operate high-performance backend services (FastAPI, gRPC, async systems, messaging) that power orchestration, tool execution, and agent runtime behavior.

Own observability and reliability for non-deterministic systems, delivering end-to-end tracing, monitoring, and cost/performance visibility for agent executions.

Manage cloud-native infrastructure and deployment, including Kubernetes workloads, containerized services, CI/CD pipelines, and resource optimization (CPU/memory, autoscaling).