Responsibilities
Architect backend MCP services to enable seamless context exchange between browsers and LLMs.
Implement secure multi-tenant gateways with dynamic API key routing, request-level caching, and adaptive throughput control.
Develop a unified tool invocation layer exposing JSON-RPC interfaces and integrating with Chromium extensions.
Collaborate with frontend and browser teams to ensure ultra-low-latency MCP signaling ( Evolve MCP specifications aligned with open-source developments and maintain backward compatibility.
Requirements
3+ years of experience delivering Python backend systems, proficient in asyncio, FastAPI, pydantic, and high-performance libraries.
Strong background in distributed caching (e.g., Redis Streams), messaging systems(Kafka, Pulsar), and PostgreSQL tuning.
Hands-on expertise in authorization/authentication protocols (OAuth 2.0, JWT, SAML) and multi-tenant isolation strategies.
Skilled in container orchestration and CI/CD practices using Docker and Kubernetes.
Demonstrated ability to interpret and implement English-language technical documentation and community contributions.
Preferred Qualifications
Contributions to MCP or related official repositories.
Experience with Chromium Extension / Native Messaging, WebSocket, and Chrome DevTools Protocol.
Experience building Agent backend systems (e.g., AutoGPT, Copilot, ChatGPT Plugin).
Familiarity with LLM inference acceleration (vLLM, TensorRT-LLM) or prompt caching optimization.
#J-18808-Ljbffr