About Bolter
Bolter is an AI agent platform built to help people get real work done, without needing to stitch together multiple tools or spend weeks setting things up.
You describe what you need in plain language and Bolter creates and runs agents that can carry out the work end to end. They retain context, remember how you work and can also create real, shareable apps such as trackers and dashboards.
Bolter is funded and currently at the validation-sprint stage, working with a small group of high-impact operators. The product already exists. We are now looking for a founding designer to lead a significant redesign and establish the design foundations for what comes next.
About the role
As Bolter's product engineer, you will own the full lifecycle of the product - from rapid prototyping to production - across the agent-building experience, the workspace where people steer their agents, and the applications those agents generate.
This is a role for someone who cares as much about the product as the code. You'll work directly with the GM in a lean team, with specialised AI agents supporting implementation. The product is early enough that the core technical decisions are open, and your work will shape how Bolter develops from here.
You'll own the three fundamental technical challenges:
1. The agent runtime - creating and running agents end to end
Bolter's core promise is that agents carry out real work from a plain-language description. You'll design and build the pipeline that turns a description into a working, reliable agent - one that retains context, remembers how its user works, and produces real, shareable output.
2. The workspace and agent-generated applications
People don't just talk to agents; they steer them and use what they produce. You'll build the workspace where users understand, direct and trust their agents, and the infrastructure that lets agents create real, usable apps - trackers, dashboards, tools.
3. Production reliability - making agents trustworthy enough to ship
Agents that do real work need to be dependable. You'll own the reliability layer - evals, error handling, and the systems that make agent output something users can actually rely on, not just demo.
What you’ll do
Own the technical roadmap across the three domains above, from research and prototyping through production.
Make architecture calls with real trade-offs - speed, reliability, cost, build vs buy, where AI does the work and where humans steer.
Ship working prototypes fast and harden what works. This is a validation-stage environment; polish comes after proof.
Use AI tools as a multiplier. We run lean, with a small human core augmented by a fleet of specialised AI agents for implementation.
Recruit and shape the early engineering team as we scale.
Stay close to the product. You'll work directly with the GM - expect to have strong opinions on UX, not just infrastructure.
Why you're made for this
A track record of shipping production software - ideally founding or early-engineer experience at a product-led startup.
Strong TypeScript across the full stack - this is the core of the role and our app stack. Some Go where it fits.
Depth in at least one of: LLM application design and production AI reliability, real-time data infrastructure, or building developer-facing products and internal tooling.
Strong product instincts - you connect technical choices to user outcomes and business impact.
Comfort prototyping fast and loose to prove a feature out, then shifting into steady-state mode to harden what's worth keeping - tests, edge cases, reliability.
Genuine interest in messaging applications and productivity - or AI messaging applications and AI. This is a product about people getting real work done through agents, and we want someone who cares about that category.
You're opinionated but calibrated - you can defend a position and change your mind when the evidence shifts.
You write clearly. Technical communication is a first-class skill in this role.
You're comfortable with ambiguity. Many of the problems we're solving don't have textbook answers.
You can leverage AI agents as a force multiplier - we run lean, with a small human core augmented by a fleet of specialised agents.
You care about craft, but you ship.
Bonus points
Experience building AI products, productivity tools, or chat applications - anything where an agent or assistant does real work for a user.
Built consumer-facing productivity or messaging applications - at scale is a strong reference.
A good grasp of what makes AI and productivity products good - you know the competitive landscape and what separates the best from the rest.
Experience with LLM evals, hallucination mitigation, or production AI reliability at scale.
Experience with real-time streaming architectures and event-driven systems.
A public portfolio - open source, papers, blog posts, side projects. We love builders who ship outside work too.
Comfort operating across the stack, from back-end services up to frontend UX.
While we think the above experience could be important, we're keen to hear from people who believe they have valuable experience to bring to the role. If you identify with the team and mission, but not all of our requirements, then please still apply!