Senior Software Engineer, AI Gateway

About Docker Docker has been one of the most loved brands in developer tooling, trusted by more than 20 million monthly users and over 20 billion container image pulls. From solo founders to the world's largest companies, developers rely on Docker to build, share, and run their applications across our suite of products including Docker Desktop, Docker Hub, and Docker Scout. We are a globally distributed, remote-first team building the tools that define how software gets built and delivered. As AI agents redefine software development, Docker is at the center of that shift, providing the sandboxed environments, verified images, and secure infrastructure that make autonomous workflows trustworthy by default. _______________________________________________________________________ Docker AI Gateway is our answer to the complexity of taking AI agents from prototype to production. It’s a powerful, intelligent, and secure control point that eliminates the toil of model orchestration, tool management, observability, and governance—so developers can focus on building incredible AI agents, not gluing together infrastructure. The Gateway sits at the center of modern AI applications, offering: A model and tool routing layer with built-in security and cost optimization A familiar OpenAI-compatible interface and MCP server Unified observability and policy enforcement Auto-RAG, tool injection, session summarization, and more We’re just getting started—and we need exceptional engineers to help us build the backbone of the future of agent-based development. What You’ll Do Design and implement core systems powering the AI Gateway, including the model router, MCP gateway, and control plane Build infrastructure that supports dynamic model selection/routing, auto-failover, cost-based routing, and policy enforcement Own critical capabilities such as secure credential storage, session summarization, caching, and rate limiting Develop APIs for developers building with OpenAI-compatible interfaces and the Model Context Protocol Build the underlying infrastructure to support evaluation, telemetry, replay, and backtesting for agents and LLM workflows Lead architectural decisions and mentor engineers as the team scales Performance tuning - caching, session summarization, and rate limiting that keep the gateway fast under real production load Contribute to roadmap planning, technical strategy, and cross-functional alignment Key Problems You’ll Help Solve Building a unified abstraction over fundamentally different model and tool providers without leaking their differences into the developer experience Making credential and identity handling for tool access both airtight and fast Giving developers real-time and historical visibility into what their agents are doing, with policy enforcement that can't be bypassed Keeping latency low and reliability high as traffic scales from early adopters to production fleets Who You Are Required Qualifications: 6+ years of backend engineering experience with production-grade systems Deep knowledge of distributed and highly scalable systems, cloud-native infrastructure, and API design Experience building secure, high-throughput services (e.g., gateways, proxies, load balancers, policy engines) Fluency in Go, and/or Rust (both preferred) Familiarity with AI/ML platforms or model serving infrastructure A strong product mindset—you're excited about building developer-facing tools Ownership mentality with a bias for shipping, learning, and iterating Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience Bonus Qualifications: Prior experience with OpenAI, Anthropic, or similar LLM APIs Familiarity with RAG architectures, vector databases, or agent frameworks (e.g., LangChain, AutoGPT, CrewAI) Experience with policy engines (e.g., OPA), observability frameworks (e.g., OpenTelemetry), or API gateways Understanding of OAuth2.1, secret management, and cloud IAM