Software Engineer

MintMCP•San Francisco, CA

4d•Onsite

About The Position

MintMCP is an AI-native startup focused on enabling companies to safely put agents to work. Their first product is an MCP gateway that provides governed access to company data and tools for agents, ensuring security through scoped permissions and detailed audit logs. The company is expanding its agent stack to include connectors, monitoring, sandboxing, long-running agents, and memory, aiming to become the core operating system for a company's work. The team operates in person in the San Francisco Bay Area with a flat structure, offering significant autonomy. Employees leverage AI tools like Claude and Codex daily, with agents actively participating in coding, code reviews, and operational tasks. Since launching in February 2026, MintMCP has acquired over 50 paying customers, including Coursera, Arlo, and Braze, and is backed by prominent investors and industry leaders. The Software Engineer role involves end-to-end feature ownership across gateway infrastructure, enterprise deployments, and agentic systems. While the role leans towards backend and infrastructure, engineers are expected to contribute across the stack, including UI development and connector maintenance. The primary working environment involves AI tools and agents, with a focus on judgment, architecture, product decisions, and ensuring the quality of AI-generated code. The company emphasizes rapid shipping, direct learning from founders and customers, and offers roles across various experience levels, prioritizing judgment, range, and shipping speed.

Requirements

Track record of shipping to real users (product, internal tool, open-source project, or serious side project).
Ability to ship and iterate without waiting for specs or approvals.
Strong fundamentals and ability to learn fast.
Focus on product value and customer needs over technical purity.
Understanding of infrastructure concepts like blast radius and trust boundaries.
Ability to read unfamiliar code, reason from first principles, and explain tradeoffs.
Comfort across the stack (TypeScript, Python, CockroachDB) or ability to pick up new technologies quickly.
Excitement to build with agents and understand their capabilities and limitations.
Experience building with AI daily and a desire for a less process-heavy environment.

Nice To Haves

Developer-facing products, protocol or gateway work, or infrastructure at scale.
Background in security, identity, or permission systems.
Contributions to open source, MCP servers, or agentic frameworks.
Design sensibility (engineers who care about design, designers who think about infrastructure).

Responsibilities

Own features end to end, from conception to production, across gateway infrastructure, enterprise deployments, and agentic systems.
Contribute across the full stack, including backend, infrastructure, UI development, and connector maintenance.
Utilize AI tools and agents as a primary working environment for development and operations.
Apply judgment to shape problems, make architectural and product decisions, and harden enterprise paths.
Design connectors, protect security-sensitive surfaces, and ensure the quality of AI-generated code.
Collaborate directly with founders and customers to understand needs and product direction.
Learn and adapt quickly to new technologies, languages, protocols, and domains.
Contribute to building and deploying agents on the company's platform.