What We're Looking For
· 5+ years of professional software engineering, with at least 2 years focused on applied AI in production systems.
· Proficient in Python and/or Go; comfortable reading and writing in the other.
· Proven experience building and scaling multi-agent or agent-driven systems in production — real-world operational ownership, not just simple LLM workflows.
· Hands-on experience with modern agent ecosystems, including frameworks (e.g., LangGraph, Google ADK, Mastra, Claude Agent SDK), observability and evals tooling (e.g., Langfuse, LangSmith, Braintrust), MCP implementations, and leading AI SDKs (e.g., OpenAI, Anthropic).
· Strong systems and backend architecture fundamentals — designing scalable, reliable systems and handling infrastructure, performance, failure modes, cost, and deployment concerns.
· Good understanding of cloud-native environments (Google Cloud Platform and/or AWS) — compute, storage, networking, and managed AI services.
· Experience designing and integrating with enterprise APIs (REST, GraphQL) including authentication and authorization patterns (OAuth2, SAML, API keys, RBAC). Comfortable working with backend databases (SQL and NoSQL) — writing queries, understanding data models, and building data access layers that enforce role-based access control.
· Strong cross-functional collaborator and communicator, able to partner with Product, Operations, and domain experts to deliver end-to-end systems with measurable real-world impact.
· A force-multiplier on the team — you raise the bar for clarity of thinking, system design standards, and team execution.
Nice to Have
· Experience with AI evaluation tooling (Langfuse, LangSmith, Braintrust, or custom eval frameworks).
· Experience building custom MCP servers, not just consuming them.
· Familiarity with containerization and orchestration (Docker, Kubernetes).
· AI-native builder with high velocity and ownership — intellectual curiosity, rapid adoption of new tools, bias to action, and the ability to drive ambiguous problems from concept to production.
· Hands-on experience with inference cost optimization — managing spend as agent deployments scale.
· Experience using AI-powered coding agents (e.g., Claude Code, GitHub Copilot, Cursor, Windsurf) to accelerate development workflows — rapid prototyping, code generation, debugging, and test writing.
· Experience with RAG (Retrieval-Augmented Generation) architectures and document retrieval pipelines — vector databases, embedding models, chunking strategies, and hybrid search — for building agents that answer questions grounded in enterprise documentation.
