Site Reliability Engineer
Software/AI Engineer
Remotefulltime
Apply on the employer's siteRole description
Client Information
An innovative company is the AI coworker. It lives in Slack and Microsoft Teams, connects to thousands of tools, and does real work for real companies: finance, marketing, ops, engineering. We're building the product that replaces half the SaaS stack with a single teammate.
Software/AI Engineer
Build and enhance AI agents for Slack and Teams, integrating tools, ensuring reliability, and shipping code to production daily in a fast-paced, small team environment.
Mid-Senior. Full-time. Remote. Germany
Required Skills
TypeScript. React. Python. AI-assisted development. Container orchestration
Requirements
- Experience building or significantly modifying AI agents
- Fluency in agentic coding workflows
- Experience with systems thinking and technical trade-offs
- Ability to ship to production quickly
- Onsite work in Munich, New York, or Warsaw
Build and enhance AI agents for Slack and Teams, integrating tools, ensuring reliability, and shipping code to production daily in a fast-paced, small team environment.
The short version
You're the person who makes the product do more things, for more customers, more reliably. You've built agents before — runtime, tools, memory, evals — and you have opinions about what makes them work. You ship to production the day you wrote the code. AI-assisted development is how you work by default, because that's how you're fastest.
If you've never built an agent, this isn't the role. We're hiring people who already have the muscle and want to build the agent everyone else will try to copy.
What's actually going on
Someone in Slack asks the product to reconcile their Stripe payouts against their books. It does it, live, in under a minute. The customer tells their network. Two more teams sign up that week. That's the loop. Your job is to make it happen more often, across more surfaces, more reliably.
600K+ tool calls a day. Volume curve is steep. Connections to thousands of tools — Salesforce, Notion, Stripe, QuickBooks, HubSpot, Shopify, whatever customers ask for next. Each new integration unlocks a new shape of customer. Each reliability win compounds.
What you'll do
Build the agent runtime. Sandboxed execution, tool orchestration, memory, the closed loop where the agent checks its own work. The layer that turns a sentence in Slack into a real action against a real API — and verifies it landed.
Ship integrations. OAuth, webhooks, schema mapping, error handling. The bar is that it works on the customer's actual data on day one, not on a fixture.
Run the infrastructure. Container orchestration, autoscaling, cost per task. The product stays fast and cheap because you're paying attention to it.
Ship product. Features that go directly to users through Slack and Teams. You'll see people using what you built within hours.
Whatever needs building. Small team, large surface. You'll work on things that aren't in this document.
How you'll know it's working
You ship to production every day and the changelog has your name on it. A feature you built is the reason a customer closed. When something breaks at 3am, you can fix it because you understand the system end to end. The founders are writing less code because you've taken over surfaces they used to own.
Week one: ship something to production. Take ownership of a live surface.
You
Personally built or significantly modified an AI agent harness — you can describe the trade-offs you made and why
Made an agent reliably close the loop: tests, linters, typecheckers, verification, whatever it took to get the agent to check its own work instead of hallucinating success
Built custom skills, CLIs, or MCP servers to make your own agentic coding faster — you don't just use the tools shipped to you
Agentic coding is your daily workflow. Informed opinions about which models, harnesses, and tools to reach for and when — stress-tested across the frontier, not just settled on one
Systems thinking: hard technical trade-offs, understanding how things break at scale, good judgment about what's worth doing well vs. fast
Range: agent runtime to React component to deployment script in an afternoon
Genuine interest in how AI actually works — you've read papers, read other people's prompts, have opinions about evals
This role doesn't work without agentic coding fluency. If AI-assisted development isn't already how you work, you'll be behind on day one.
Why this role is different
No layers. You work directly with both founders. Decisions get made in the room, not in a ticket.
The agent is the product. You're not bolting AI onto something — you're building the thing customers came for. Every reliability win, every new tool, every memory improvement shows up in retention the next week.
Volume that forces you to be good. 600K+ tool calls a day means the lazy answer breaks in production immediately.
The feedback loop is hours, not quarters. Ship in the morning, customer uses it in the afternoon, you see what worked by end of day.
Even better if
Previous founder or early-stage builder · Open source contributions to AI tooling · Deep model understanding and eval infrastructure experience
Tech
TypeScript/React on the frontend · Python on the backend and agents · Modal for infrastructure. You don't need to know all of it coming in. You need to learn fast.
How we work
Small team, high trust, low process. Ship your first week. Talk to users your first day. Everyone owns something real — not a task, a surface of the company customers depend on. You'll use the product to build the product and see the impact daily.
Competitive salary · Meaningful equity · The kind of ownership that only exists at this stage
**Briefing Notes**
Mission & Context
We are sourcing for a rapidly scaling AI startup building an autonomous digital teammate that executes complex enterprise work. This is a foundational engineering role to build the core agent runtime, integrations, and infrastructure. The hire will work directly with the founders to significantly enhance the product's capabilities and reliability as the company scales.
Candidate Overview
The ideal candidate is a strong full-stack engineer based in Germany with deep proficiency in both Python and TypeScript/React. They must have demonstrable experience building complex, scalable systems (not just websites) and thrive in a high-ownership, fast-paced startup environment. A genuine, proven interest in AI, demonstrated through personal projects or heavy use of AI development tools, is non-negotiable.
Green Flags
- Experience at another early-stage AI or developer tool startup.
- Public portfolio (e.g., GitHub) with personal projects involving AI agents, complex system design, or API integrations.
- Contributions to open-source AI, agent, or infrastructure projects.
- History of shipping code daily or multiple times per day in a CI/CD environment.
- Experience building products with a chat-based (e.g., Slack, Teams) user interface.
Red Flags
- Candidate is not located in Germany or does not have the right to work there.
- Career history is exclusively in large, slow-moving corporate environments with siloed roles.
- Profile shows only frontend or only backend experience with no evidence of working across the stack.
- Expresses a need for structured management, mentorship programs, or a well-defined career path.
- Cannot speak to their personal or professional use of AI tools like GitHub Copilot.
- Shows discomfort with the expectation to resolve production issues independently, potentially outside of standard hours.
Vibe Check
The founders are looking for a 'builder' who is obsessed with shipping product, not a 'theorist' who enjoys meetings. The ideal candidate is energized by the idea of high ownership, direct user feedback, and seeing their code go live the same day they write it. They should be comfortable with the intensity and accountability of an early-stage venture.
Nice-to-Haves
- Experience building and maintaining third-party API integrations (e.g., Salesforce, Stripe, HubSpot).
- Experience with infrastructure management, cost optimization, and DevOps practices.
- Experience building sandboxed execution environments.
- Prior experience working effectively in a fully remote, asynchronous team.
- Experience building developer tools or platforms.
Soft Skills
- Extreme ownership and autonomy.
- High agency and a bias for action.
- Pragmatic and product-driven mindset.
- Strong written communication skills (critical for async work).
- Resilience and a calm, problem-solving approach under pressure.
- Comfort with ambiguity and rapid change.
Visa & Work Authorization
This is a remote position, but candidates must be located in and have the existing right to work in Germany. The team meets in person a few times a year, so the ability to travel for these gatherings is expected. The company is not offering visa sponsorship at this time.
Fill in the form, we will contact you...
This is a saved copy of a posting published elsewhere. Postings get taken down without notice — check the employer's site before applying. mentors.coach is not the hiring party.