Software Engineer
MintMCP · San Francisco, CA · 1 mo ago
HybridInformation TechnologyFull-time
We need to output HTML fragment with sections: About Us, The Job, About You, What we offer (maybe Benefits). Use for each section heading. Use
for each section heading. Use - for lists. Use
for prose. Do not repeat job title. No Job ID. Remove boilerplate like cookie/navigation/legal/EEO etc. There's none. Need to preserve all substantive info.
We need to parse the posting: It includes sections: About Us (first paragraph), then "AI-Native Startup", "Traction", "The Job", "About You", "What we offer". Also there is a line "Prefer to have your agent apply? Point it at https://www.mintmcp.com/hiring/mcp" which is application instruction; we should remove that.
We need to decide which headings to include: About Us, The Job, About You, What we offer (Benefits). Possibly also "Traction" and "AI-Native Startup" could be part of About Us? The instruction: use headings for section headings like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. But we can also use other headings if they exist? The instruction says: use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It suggests those are examples, but we can use other headings if they are present? Probably we should map content to those standard headings where appropriate. However we must include a section only when posting has real specific content for it. The posting includes "About Us", "The Job", "About You", "What we offer". There's no explicit Responsibilities, Requirements, etc. But we could treat "The Job" as responsibilities. "About You" as requirements/qualifications. "What we offer" as benefits. "About Us" as about the company.
Thus we can output sections: About Us, The Job, About You, Benefits (What we offer). Use for each.
Inside each, we need to format content: paragraphs and lists.
Let's extract content.
About Us: The block from "About Us MintMCP helps companies..." up to before "AI-Native Startup". Let's copy:
"About Us MintMCP helps companies put agents to work safely. We exist to help companies do more of their work with agents, and we build the infrastructure that makes a company's own work runnable by them. That has to start from trust. Our first product is an MCP gateway that gives those agents governed access to company data and tools. Before agents can touch Slack, GitHub, Jira, Snowflake, internal databases, or production systems, you need to know what they can reach, what they did, and why they were allowed to do it. Most people carry far more permissions than any single task needs. If an agent uses your token directly, it inherits all of them. MintMCP scopes that access down to exactly what an agent needs to do its job and captures the data flows and audit logs security teams need. From there 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 work in person in the San Francisco Bay Area. The structure is flat and the market moves fast, so you have a lot of latitude over what you work on and how."
We need to ensure no duplication. That's fine.
Next "AI-Native Startup" block: "AI-Native Startup We are AI-native. Everyone uses Claude and Codex every day, and we have more agents than employees. They run in Slack alongside the team, write code, review PRs, and handle sales, marketing, and deal ops on the same gateway we sell to customers. We are building an entire company operating system around them, and you will help build it."
Then "Traction": "Traction Since launching in February 2026, we have grown to 50+ paying customers, with strong inbound demand. Customers include Coursera, Arlo, and Braze. We are backed by Cowboy Ventures and Coatue, with angels including Frederic Kerrest (Okta), Michael Grinich (WorkOS), Andrej Karpathy, Jeff Dean, and Scott Belsky. Our founders are machine learning experts from Stanford, Berkeley, and CMU, with applied research at Google Brain and Waymo, and one co-founded Coursera."
We could incorporate AI-Native Startup and Traction into About Us section as additional paragraphs, or maybe separate sections? The instruction says prefer few substantive sections over many thin ones. So we could merge AI-Native Startup and Traction into About Us as extra paragraphs. That seems fine.
Then "The Job": block from "The Job You will own features end to end..." up to before "About You". Let's extract:
"The Job 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. We hire across levels, from strong early-career builders to seasoned engineers, and we set level and pay to match. What matters most is judgment, range, and how fast you ship."
We need to ensure no duplication.
Then "About You": block from "About You You are a builder..." up to before "What we offer". Let's extract:
"About You You are a builder with a track record of shipping to real users, whether that is a product, an internal tool, an open-source project, or a serious side project. You ship, then iterate, without waiting for specs or approvals. You have strong fundamentals and learn fast. How quickly you pick things up matters as much as years of experience. You care about product value and customer needs over technical purity. You take infra seriously. You think about blast radius, trust boundaries, and what happens when your code is in the path of every customer's agents. You can read unfamiliar code, reason from first principles, and explain your tradeoffs. You are comfortable across the stack (TypeScript, Python, CockroachDB), or you pick up new languages, protocols, and domains fast. You are excited to build with agents, and to learn when they help and when they hide a problem. You already build with AI every day and want 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. Design sensibility: engineers who care about design, designers who think about infrastructure."
We need to format Nice to have as a list maybe.
Then "What we offer": block from "What we offer: Competitive compensation and meaningful equity." up to before "Prefer to have your agent apply?".
Extract:
"What we offer: Competitive compensation and 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, on a team that puts family and health first."
We need to format as benefits section with list.
Now produce HTML:
About Us
... paragraphs ... maybe split into multiple
for readability.
We could break into paragraphs: first paragraph about mission, second about product, third about work environment.
Let's craft:
Paragraph1: "MintMCP helps companies put agents to work safely. We exist to help companies do more of their work with agents, and we build the infrastructure that makes a company's own work runnable by them. That has to start from trust."
Paragraph2: "Our first product is an MCP gateway that gives those agents governed access to company data and tools. Before agents can touch Slack, GitHub, Jira, Snowflake, internal databases, or production systems, you need to know what they can reach, what they did, and why they were allowed to do it. Most people carry far more permissions than any single task needs. If an agent uses your token directly, it inherits all of them. MintMCP scopes that access down to exactly what an agent needs to do its job and captures the data flows and audit logs security teams need."
Paragraph3: "From there 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 work in person in the San Francisco Bay Area. The structure is flat and the market moves fast, so you have a lot of latitude over what you work on and how."
Paragraph4: "We are AI-native. Everyone uses Claude and Codex every day, and we have more agents than employees. They run in Slack alongside the team, write code, review PRs, and handle sales, marketing, and deal ops on the same gateway we sell to customers. We are building an entire company operating system around them, and you will help build it."
Paragraph5: "Since launching in February 2026, we have grown to 50+ paying customers, with strong inbound demand. Customers include Coursera, Arlo, and Braze. We are backed by Cowboy Ventures and Coatue, with angels including Frederic Kerrest (Okta), Michael Grinich (WorkOS), Andrej Karpathy, Jeff Dean, and Scott Belsky. Our founders are machine learning experts from Stanford, Berkeley, and CMU, with applied research at Google Brain and Waymo, and one co-founded Coursera."
That covers About Us.
Now The Job section: maybe break into paragraphs.
Paragraph1: "You will own features end to end, from conception to production, across our gateway infrastructure, enterprise deployments, and agentic systems."
Paragraph2: "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."
Paragraph3: "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."
Paragraph4: "Roles are blurred and we ship within hours, and you will learn directly from the founders and from customers. We hire across levels, from strong early-career builders to seasoned engineers, and we set level and pay to match. What matters most is judgment, range, and how fast you ship."
Now About You section: we can have paragraphs and a list for Nice to have.
Paragraph1: "You are a builder with a track record of shipping to real users, whether that is a product, an internal tool, an open-source project, or a serious side project. You ship, then iterate, without waiting for specs or approvals. You have strong fundamentals and learn fast. How quickly you pick things up matters as much as years of experience."
Paragraph2: "You care about product value and customer needs over technical purity. You take infra seriously. You think about blast radius, trust boundaries, and what happens when your code is in the path of every customer's agents. You can read unfamiliar code, reason from first principles, and explain your tradeoffs."
Paragraph3: "You are comfortable across the stack
for prose. Do not repeat job title. No Job ID. Remove boilerplate like cookie/navigation/legal/EEO etc. There's none. Need to preserve all substantive info. We need to parse the posting: It includes sections: About Us (first paragraph), then "AI-Native Startup", "Traction", "The Job", "About You", "What we offer". Also there is a line "Prefer to have your agent apply? Point it at https://www.mintmcp.com/hiring/mcp" which is application instruction; we should remove that. We need to decide which headings to include: About Us, The Job, About You, What we offer (Benefits). Possibly also "Traction" and "AI-Native Startup" could be part of About Us? The instruction: use headings for section headings like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. But we can also use other headings if they exist? The instruction says: use
for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). It suggests those are examples, but we can use other headings if they are present? Probably we should map content to those standard headings where appropriate. However we must include a section only when posting has real specific content for it. The posting includes "About Us", "The Job", "About You", "What we offer". There's no explicit Responsibilities, Requirements, etc. But we could treat "The Job" as responsibilities. "About You" as requirements/qualifications. "What we offer" as benefits. "About Us" as about the company.
Thus we can output sections: About Us, The Job, About You, Benefits (What we offer). Use for each.
Inside each, we need to format content: paragraphs and lists.
Let's extract content.
About Us: The block from "About Us MintMCP helps companies..." up to before "AI-Native Startup". Let's copy:
"About Us MintMCP helps companies put agents to work safely. We exist to help companies do more of their work with agents, and we build the infrastructure that makes a company's own work runnable by them. That has to start from trust. Our first product is an MCP gateway that gives those agents governed access to company data and tools. Before agents can touch Slack, GitHub, Jira, Snowflake, internal databases, or production systems, you need to know what they can reach, what they did, and why they were allowed to do it. Most people carry far more permissions than any single task needs. If an agent uses your token directly, it inherits all of them. MintMCP scopes that access down to exactly what an agent needs to do its job and captures the data flows and audit logs security teams need. From there 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 work in person in the San Francisco Bay Area. The structure is flat and the market moves fast, so you have a lot of latitude over what you work on and how."
We need to ensure no duplication. That's fine.
Next "AI-Native Startup" block: "AI-Native Startup We are AI-native. Everyone uses Claude and Codex every day, and we have more agents than employees. They run in Slack alongside the team, write code, review PRs, and handle sales, marketing, and deal ops on the same gateway we sell to customers. We are building an entire company operating system around them, and you will help build it."
Then "Traction": "Traction Since launching in February 2026, we have grown to 50+ paying customers, with strong inbound demand. Customers include Coursera, Arlo, and Braze. We are backed by Cowboy Ventures and Coatue, with angels including Frederic Kerrest (Okta), Michael Grinich (WorkOS), Andrej Karpathy, Jeff Dean, and Scott Belsky. Our founders are machine learning experts from Stanford, Berkeley, and CMU, with applied research at Google Brain and Waymo, and one co-founded Coursera."
We could incorporate AI-Native Startup and Traction into About Us section as additional paragraphs, or maybe separate sections? The instruction says prefer few substantive sections over many thin ones. So we could merge AI-Native Startup and Traction into About Us as extra paragraphs. That seems fine.
Then "The Job": block from "The Job You will own features end to end..." up to before "About You". Let's extract:
"The Job 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. We hire across levels, from strong early-career builders to seasoned engineers, and we set level and pay to match. What matters most is judgment, range, and how fast you ship."
We need to ensure no duplication.
Then "About You": block from "About You You are a builder..." up to before "What we offer". Let's extract:
"About You You are a builder with a track record of shipping to real users, whether that is a product, an internal tool, an open-source project, or a serious side project. You ship, then iterate, without waiting for specs or approvals. You have strong fundamentals and learn fast. How quickly you pick things up matters as much as years of experience. You care about product value and customer needs over technical purity. You take infra seriously. You think about blast radius, trust boundaries, and what happens when your code is in the path of every customer's agents. You can read unfamiliar code, reason from first principles, and explain your tradeoffs. You are comfortable across the stack (TypeScript, Python, CockroachDB), or you pick up new languages, protocols, and domains fast. You are excited to build with agents, and to learn when they help and when they hide a problem. You already build with AI every day and want 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. Design sensibility: engineers who care about design, designers who think about infrastructure."
We need to format Nice to have as a list maybe.
Then "What we offer": block from "What we offer: Competitive compensation and meaningful equity." up to before "Prefer to have your agent apply?".
Extract:
"What we offer: Competitive compensation and 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, on a team that puts family and health first."
We need to format as benefits section with list.
Now produce HTML:
About Us
About Us
... paragraphs ... maybe split into multiple
for readability.
We could break into paragraphs: first paragraph about mission, second about product, third about work environment. Let's craft: Paragraph1: "MintMCP helps companies put agents to work safely. We exist to help companies do more of their work with agents, and we build the infrastructure that makes a company's own work runnable by them. That has to start from trust." Paragraph2: "Our first product is an MCP gateway that gives those agents governed access to company data and tools. Before agents can touch Slack, GitHub, Jira, Snowflake, internal databases, or production systems, you need to know what they can reach, what they did, and why they were allowed to do it. Most people carry far more permissions than any single task needs. If an agent uses your token directly, it inherits all of them. MintMCP scopes that access down to exactly what an agent needs to do its job and captures the data flows and audit logs security teams need." Paragraph3: "From there 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 work in person in the San Francisco Bay Area. The structure is flat and the market moves fast, so you have a lot of latitude over what you work on and how." Paragraph4: "We are AI-native. Everyone uses Claude and Codex every day, and we have more agents than employees. They run in Slack alongside the team, write code, review PRs, and handle sales, marketing, and deal ops on the same gateway we sell to customers. We are building an entire company operating system around them, and you will help build it." Paragraph5: "Since launching in February 2026, we have grown to 50+ paying customers, with strong inbound demand. Customers include Coursera, Arlo, and Braze. We are backed by Cowboy Ventures and Coatue, with angels including Frederic Kerrest (Okta), Michael Grinich (WorkOS), Andrej Karpathy, Jeff Dean, and Scott Belsky. Our founders are machine learning experts from Stanford, Berkeley, and CMU, with applied research at Google Brain and Waymo, and one co-founded Coursera." That covers About Us. Now The Job section: maybe break into paragraphs. Paragraph1: "You will own features end to end, from conception to production, across our gateway infrastructure, enterprise deployments, and agentic systems." Paragraph2: "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." Paragraph3: "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." Paragraph4: "Roles are blurred and we ship within hours, and you will learn directly from the founders and from customers. We hire across levels, from strong early-career builders to seasoned engineers, and we set level and pay to match. What matters most is judgment, range, and how fast you ship." Now About You section: we can have paragraphs and a list for Nice to have. Paragraph1: "You are a builder with a track record of shipping to real users, whether that is a product, an internal tool, an open-source project, or a serious side project. You ship, then iterate, without waiting for specs or approvals. You have strong fundamentals and learn fast. How quickly you pick things up matters as much as years of experience." Paragraph2: "You care about product value and customer needs over technical purity. You take infra seriously. You think about blast radius, trust boundaries, and what happens when your code is in the path of every customer's agents. You can read unfamiliar code, reason from first principles, and explain your tradeoffs." Paragraph3: "You are comfortable across the stack