Description

Design and govern production-grade agentic systems with tool orchestration, memory, and MCP integrations.

This role is hybrid.

Responsibilities

• Build agentic systems implementing tool orchestration, memory management, and MCP integrations.
• Implement AI governance patterns including guardrails, data lineage, and auditability.
• Develop automated evaluations, simulation tests, and regression frameworks to ensure system reliability.
• Drive adoption through pilots and scalable implementations across engineering teams.
• Collaborate with product and security teams to deliver production-grade end-to-end solutions.

Required Skills

• 5+ years professional software engineering, with 2+ years in applied AI production systems.
• Proficient in Python and/or Go; able to read and write in the other.
• Proven experience scaling multi-agent or agent-driven systems in production.
• Hands-on experience with LangGraph, Google ADK, Mastra, or Claude Agent SDK.
• Strong backend architecture fundamentals for scalable, reliable systems.
• Experience with GCP and/or AWS cloud-native environments.
• Designing and integrating REST or GraphQL APIs with authentication patterns.
• Working with SQL and NoSQL databases, including RBAC enforcement.

Preferred Skills

• Experience with AI evaluation tools like Langfuse, LangSmith, or Braintrust.
• Building custom MCP servers.
• Familiarity with Docker and Kubernetes containerization.

Key Skills

Education

Any Graduate