Staff Software Engineer, AI Gateway

At Docker, we make app development easier so developers can focus on what matters. Our remote-first team spans the globe, united by a passion for innovation and great developer experiences. With over 20 million monthly users and 20 billion image pulls, Docker is the #1 tool for building, sharing, and running apps—trusted by startups and Fortune 100s alike. We’re growing fast and just getting started. Come join us for a whale of a ride! 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 optimizationA familiar OpenAI-compatible interface and MCP serverUnified observability and policy enforcementAuto-RAG, tool injection, session summarization, and moreWe’re just getting started—and we need exceptional engineers to help us build the backbone of the future of agent-based development. ResponsibilitiesDesign and implement core systems powering the AI Gateway, including the model router, MCP gateway, and control planeBuild infrastructure that supports dynamic model selection, auto-failover, cost-based routing, and policy enforcementOwn critical capabilities such as secure credential storage, session summarization, caching, and rate limitingDevelop APIs for developers building with OpenAI-compatible interfaces and the Model Context ProtocolBuild the underlying infrastructure to support evaluation, telemetry, replay, and backtesting for agents and LLM workflowsLead architectural decisions and mentor engineers as the team scalesCollaborate with product and design to create delightful experiences in our control plane UIContribute to roadmap planning, technical strategy, and cross-functional alignmentKey Problems You’ll Help SolveBuild a unified abstraction layer across diverse model and tool providers (OpenAI, Anthropic, Google, AWS Bedrock)Implement secure and scalable identity and credential vaulting for tool and model accessCreate infrastructure to support real-time and historical analytics of AI agent behaviorEnsure policy enforcement and logging works end-to-end—from prompt to tool to responseDevelop seamless developer experiences through intuitive APIs and first-class observabilityQualifications:8+ years of backend engineering experience with production-grade systemsDeep knowledge of distributed and highly scalable systems, cloud-native infrastructure, and API designExperience 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 infrastructureA strong product mindset—you're excited about building developer-facing toolsOwnership mentality with a bias for shipping, learning, and iteratingBonus Qualifications:Prior experience with OpenAI, Anthropic, or similar LLM APIsFamiliarity 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 gatewaysUnderstanding of OAuth2.1, secret management, and cloud IAM systemsExperience with Kubernetes, Docker, and microservices architectureWe use Covey as part of our hiring and / or promotional process for jobs in NYC and certain features may qualify it as an AEDT. As part of the evaluation process we provide Covey with job requirements and candidate submitted applications. We began using Covey Scout for Inbound on April 13, 2024. Please see the independent bias audit report covering our use of Covey here. PerksFreedom & flexibility; fit your work around your lifeDesignated quarterly Whaleness DaysHome office setup; we want you comfortable while you work16 weeks of paid Parental leaveTechnology stipend equivalent to $100 net/monthPTO plan that encourages you to take time to do the things you enjoyQuarterly, company-wide hackathonsTraining stipend for conferences, courses and classesEquity; we are a growing start-up and want all employees to have a share in the success of the companyDocker SwagMedical benefits, retirement and holidays vary by countryDocker embraces diversity and equal opportunity. We are committed to building a team that represents a variety of backgrounds, perspectives, and skills. The more inclusive we are, the better our company will be. Due to the remote nature of this role, we are unable to provide visa sponsorship.#LI-REMOTE Apply to this Job