What We Are Building
Duvo is the AI operations platform for large enterprises, currently focused on retail and consumer packaged goods. Customers build AI agents in Duvo that do the work wherever it lives: SAP, spreadsheets, supplier portals, email, APIs, and more. The product is heavy on browser and computer use. Business users say what outcome they want, and the agents plan, act, ask for approval on exceptions and get better with every run.
Velocity is our moat. We ship fast and iterate even faster.
The Role
You'll own the AI platform layer that makes our agents reliable, fast and safe in production. That covers the agent runtime, context management, tool execution and orchestration, evaluation pipelines and harnesses, prompt engineering for system behaviors, and the observability tooling that lets our agents do end-to-end work for enterprise customers. You own sandbox behavior and the agent runtime logic. SRE owns the sandbox infrastructure and capacity.
This is applied AI systems engineering. You ship production systems built on LLMs, retrieval and agent orchestration, and you're accountable for their reliability, cost and quality in the real world. That includes optimizing model usage and cost, such as moving work to cheaper models like Haiku, and running self-hosted open-source models on our own GPUs.
Our product team is growing into multiple initiatives. Each one has a lead, engineers, a design engineer and an AI-focused engineer.
What We're Looking For
These are the non-negotiables, and what we'll evaluate you on:
- Production AI systems. You've made LLMs reliable at scale in production, beyond research, with hands-on experience in prompt engineering, context management, tool use or agent orchestration.
- Shipping and ownership. You've taken ambiguous AI problems to production with measurable outcomes and own the whole lifecycle: build, evaluate, deploy, monitor, iterate.
- System design for AI. You design for non-deterministic outputs, context window limits and failing tool calls. Reliability, cost and latency are first-class concerns.
- Evaluation design. You build evals that catch regressions, measure quality and give the team confidence to ship AI features. You understand failure taxonomies and know how to build meaningful test sets.
- Debugging and diagnosis. You're hypothesis-driven, tracing failures across model behavior, data pipelines and infrastructure to find the root cause.
- Judgment as AI evolves. You make build-vs-integrate calls on AI infrastructure with incomplete benchmarks and course-correct fast as models and providers change.
You Might Also
- Have designed and run distributed systems that handle high throughput and complex failure modes.
- Have a strong sense for security in AI systems: prompt injection, insecure output handling, supply chain risks.
- Have contributed to open-source AI tooling or infrastructure projects.
This Is Not For You If
- You want an ML research role. We don't train models.
- You mostly want to build user-facing product features and UI. Check out our Product Engineer role instead.
Location
We're looking for people based in Europe, in European time zones, so we overlap for most of the working day.
Our Tech Stack
- GCP (Cloud Run, GKE, GCS)
- Terraform, Docker
- Datadog
- TypeScript and Python services
- Postgres, Redis
- Latest AI primitives (Anthropic)
How We Work
- Initiative-driven. We organize around customer problems instead of org charts, then prioritize, build and ship every week.
- Customer-obsessed. We work on real problems for real customers.
- Iterative by default. We ship small, learn fast and fix forward.
- AI first. We use AI to go faster and spend human time where it matters most.
- Direct feedback. We tell each other right away what to improve.
- Autonomy with accountability. We trust people to make the call and judge them on outcomes.
What We Offer
- A competitive salary and a generous ESOP allocation in a fast-growing company, fresh off our Series A.
- Unlimited spend (within reason) on the AI tooling of your choice.
- Co-working space reimbursement if you're remote.
- Travel: frequent visits to our Prague office, offsites (including a day at the Porsche Experience Center Hockenheimring) and conferences.
- Autonomy to do your best work, including setting up meetings with people to learn from or finding a mentor.
- A real AI product used by enterprise customers. No demos, no internal tools.
- Many AI modalities in one product: voice agents, computer and browser use, reasoning, and long-running agents.
- Applied AI, not research.
- A sharp, motivated team that values ownership and candor.
How We Hire
- Application review. We read your application against what's listed under "What We're Looking For".
- Screening call (30 min). A short call with our recruiter.
- Discovery interview (30 min). A conversation with our hiring manager about your background, how you think and how you communicate.
- Technical interview (60 min). A deep dive into your technical skills with engineers from our team.
- Trial day (1 day). You work on an ambitious problem with the team, check in with one of our founders, and present what you built at the end of the day.
- Offer. If the trial day goes well, we move quickly to an offer.
