About the Role
You will own features end to end, from conception to production, across our gateway infrastructure, enterprise deployments, and agentic systems. The work leans backend and infra, but nothing is off limits: when the product needs a better UI you build it, and when a connector breaks during a security review you fix it. Claude and Codex are your primary working environment, and you use a fleet of agents to move faster than a team this size has any right to. Agents write much of the code and review PRs, so your real job is the judgment they cannot make: shaping the problem, making architecture, product, and UX calls, hardening enterprise paths, designing connectors, protecting security-sensitive surfaces, and catching generated code that is quietly wrong. Roles are blurred and we ship within hours, and you will learn directly from the founders and from customers.
Responsibilities
- Own features end to end, from conception to production
- Work across gateway infrastructure, enterprise deployments, and agentic systems
- Build UI when needed
- Fix connectors during security reviews
- Shape problems, make architecture, product, and UX calls
- Harden enterprise paths
- Design connectors
- Protect security-sensitive surfaces
- Catch generated code that is quietly wrong
Requirements
- Track record of shipping to real users (product, internal tool, open-source project, or serious side project)
- Ship and iterate without waiting for specs or approvals
- Strong fundamentals and learn fast
- Care about product value and customer needs over technical purity
- Take infra seriously, considering blast radius, trust boundaries, and impact on customer agents
- Ability to read unfamiliar code, reason from first principles, and explain tradeoffs
- Comfortable across the stack (TypeScript, Python, CockroachDB) or ability to pick up new languages, protocols, and domains quickly
- Excited to build with agents and learn their capabilities and limitations
- Comfortable building with AI every day with room to move without heavy process
- Developer-facing products experience
- Protocol or gateway work experience
- Infrastructure at scale experience
- Background in security, identity, or permission systems
- Contributions to open source, MCP servers, or agentic frameworks
- Design sensibility
Skills
- TypeScript
- Python
- CockroachDB
- AI
- Agentic systems
Location
- San Francisco Bay Area
Work Type
- In person
- Full-time
Experience Level
- Early-career builders
- Seasoned engineers
Salary/Compensations
- Competitive compensation
Benefits
- Meaningful equity
- Unusual scope and ownership of features that ship to enterprise customers
- Building and deploying agents on the same platform we sell
- Direct access to the founders, customer context, and product direction, with mentorship as you grow
- Health benefits
- Team that puts family and health first
About the Company
- MintMCP helps companies put agents to work safely by building the infrastructure that makes a company's own work runnable by them, starting with trust.
- Our first product is an MCP gateway that gives agents governed access to company data and tools, scoping access and capturing data flows and audit logs.
- We are building the rest of the agent stack: connectors, monitoring, sandboxing, long-running agents, and memory, with the goal of becoming the system a company's work runs on.
- We are an AI-native startup where everyone uses Claude and Codex daily, and we have more agents than employees.
- We are building an entire company operating system around agents.
- Since launching in February 2026, we have grown to 40+ paying customers, including Coursera, Arlo, and Braze.
- We are backed by Cowboy Ventures and Coatue, with notable angels.
- Our founders are machine learning experts from Stanford, Berkeley, and CMU, with applied research at Google Brain and Waymo, and one co-founded Coursera.
