Mintive is an AI infrastructure startup in the San Francisco Bay Area that helps companies put agents to work safely. Its first product is an MCP gateway that gives AI agents governed access to company data and tools — scoping permissions down to exactly what an agent needs and capturing the audit logs security teams require. The company is hiring a Software Engineer to own features end to end across gateway infrastructure, enterprise deployments, and agentic systems, with competitive compensation and meaningful equity. Roles are open from strong early-career builders to seasoned engineers.
About Mintive — AI Agent Infrastructure Startup
Mission: Help companies do more of their work with agents, starting from trust and governed access
First Product: An MCP gateway giving agents scoped access to tools like Slack, GitHub, Jira, Snowflake, and internal systems
Traction: 50+ paying customers since launching in February 2026, including Coursera, Arlo, and Braze
Backers: Cowboy Ventures and Coatue, plus angels including Frederic Kerrest, Michael Grinich, Andrej Karpathy, Jeff Dean, and Scott Belsky
Founders: Machine learning experts from Stanford, Berkeley, and CMU, with applied research at Google Brain and Waymo — one co-founded Coursera
Why This Software Engineer Role Stands Out
Real Ownership: Own features from conception to production that ship to enterprise customers
AI-Native Team: Everyone uses Claude and Codex daily, and the company runs more agents than employees
Founder Access: Learn directly from the founders and from customers, with mentorship as you grow
Flat Structure: Wide latitude over what you work on and how, shipping within hours
Position Overview
The Software Engineer at Mintive owns features end to end across the company’s gateway infrastructure, enterprise deployments, and agentic systems. The work leans backend and infrastructure, 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 the primary working environment, and a fleet of agents writes much of the code and reviews pull requests. Your real job is the judgment agents cannot supply — 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.
Why This Role Matters: When agents use a company’s tools, the gateway sits in the path of every request. Mistakes there affect every customer, so engineering judgment about blast radius, trust boundaries, and permissions matters more than raw output. This is a chance to build that layer early, with real customers and real security reviews, on a small team where your decisions ship.
Key Responsibilities
End-to-End Feature Ownership
- Own features from conception to production across gateway infrastructure, enterprise deployments, and agentic systems
- Build UI when the product needs it, and fix connectors fast when they break during a customer security review
- Ship in hours rather than weeks, iterating without waiting for specs or heavy approvals
Engineering Judgment in an Agent-Driven Workflow
- Use Claude, Codex, and a fleet of agents to write and review much of the code
- Shape the problem and make architecture, product, and UX decisions that agents cannot make
- Catch generated code that is quietly wrong, and know when agents help and when they hide a problem
Security, Trust & Enterprise Hardening
- Harden enterprise code paths and protect security-sensitive surfaces
- Design connectors for tools and data sources such as Slack, GitHub, Jira, Snowflake, and internal databases
- Think carefully about blast radius and trust boundaries when your code sits in the path of every customer’s agents
What Mintive Looks For
- A track record of shipping to real users — a product, internal tool, open-source project, or serious side project
- Strong fundamentals and fast learning; how quickly you pick things up matters as much as years of experience
- Care for product value and customer needs over technical purity
- Ability to read unfamiliar code, reason from first principles, and explain tradeoffs
- Comfort across the stack (TypeScript, Python, CockroachDB), or the ability to pick up new languages, protocols, and domains quickly
- Daily experience building with AI and a preference for room to move without heavy process
Nice to Have
- 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
- A design sensibility — engineers who care about design, or designers who think about infrastructure
What Mintive Offers
- Competitive compensation and meaningful equity, with level and pay set to match your experience
- Unusual scope and ownership of features that ship to enterprise customers
- Building and deploying agents on the same platform the company sells
- Direct access to the founders, customer context, and product direction, with mentorship as you grow
- Health benefits, on a team that puts family and health first
About the Opportunity — AI Agent Infrastructure in San Francisco
As more companies let AI agents touch real systems, the hard problem shifts from what agents can do to what they are allowed to do — and who can prove it afterwards. Mintive builds the access and audit layer for that world, then extends it into connectors, monitoring, sandboxing, long-running agents, and memory. For engineers who want to work on foundational infrastructure at an early stage, in the heart of the AI industry, this is a rare combination of scope, speed, and mentorship.
Career Path: Early engineers at a company like this can grow quickly into senior engineering, technical lead, or founding-team roles as the product and team expand.
Who Should Apply?
- Product-Minded Builders: Who ship quickly, iterate, and care about customer outcomes
- Backend & Infrastructure Engineers: Interested in gateways, permissions, and security-sensitive systems
- AI-Native Developers: Who already work with Claude or Codex every day and want to build agent infrastructure
- Early-Career Engineers: With a strong shipping record and fast learning curve, ready to grow under founder mentorship
- Bay Area Engineers: Ready to work in person with a small, fast-moving team
Recently opened JOBS 👇🏻
