← Все заказы

AI Product Engineer

On The Spot Development

13 ч назад

Текст заказа

About On The Spot
We bring startups and disruptive tech companies to the local market, offering engineers the opportunity to work on innovative, high-impact products. Join us and become a member of their R&D team while we take care of employment, HR support, a benefits package, and an enjoyable work environment.
About the team
Cycode is an Agentic Development Security Platform (ADSP) designed to secure the entire AI-powered development lifecycle.
By combining security scanning, AI governance, and agent-driven automation, Cycode helps organizations identify risks, understand their impact, and respond to threats at the speed modern engineering teams need.
Take a look inside Cycode’s Warsaw team in our blog post.
About the role
You will own customer problems, not tickets. An AI Product Engineer will take a problem, form a point of view, check it with customers and data, and ship it end to end. AI is how you will multiply your output, and often it will be part of what you ship.
You will work in a small, cross-functional team with product managers, designers and security researchers. The role is full stack: you will build the backend services, APIs and data, and the UI customers use to work with them. Your background is your anchor, not your boundary. When the problem needs a prompt, an evaluation set or a data pipeline, you will build it.
This is an individual contributor role, with no people management.
Stack note
Services: .NET / C#, Python
UI: React, TypeScript, Vite, TanStack Query, styled-components, Storybook, Vitest, Cypress
AI: Claude and other LLM APIs, agents, MCP servers
AI-assisted delivery: Claude Code, Cursor, shared skills and agent context files in every repo
Data: MongoDB, PostgreSQL, Redis, ArangoDB, ClickHouse
Messaging: Kafka
Platform: Kubernetes, Docker, Terraform, GitLab CI/CD
Teams own a product area end to end and decide how to solve its problems. We treat AI agents as teammates whose work gets reviewed: every repo carries the context and skills an agent needs, and engineers keep improving them.
We're open to strong backend engineers coming from Java, Go, Rust, Python, TypeScript. What matters most is solid engineering fundamentals and willingness to switch to .NET / C#.
What you'll do
Own product problems end to end. Shape the problem with product, design the solution, build it, release it and measure whether it worked.
AI-first, in how you build and in what you ship. You use AI agents (Claude Code, Cursor and similar) every day and keep improving how you use them, with the context files, skills and checks that make agents produce code you'd approve. You build AI into the product too: agents, LLM-powered triage and remediation, and MCP servers that let developers' AI assistants use Cycode. A security product can't guess, so you add evaluations, guardrails and fallbacks, measure quality, latency and cost, and choose deterministic code when it's the better answer.
Build the whole feature, backend to UI. Cloud-native .NET services, event-driven flows on Kafka and clear REST and MCP contracts, through to the React and TypeScript screens customers use. Design for partial failure and rate limits. A feature is done when a user can use it, not when the API is merged.
Operate what you build. Instrument, monitor and improve your services in production. Shipping starts the learning cycle; it doesn't end it.
Raise the bar around you. Review code and designs, share what works with AI tooling, and help shape the architecture.
What you bring
5+ years building production software, mostly backend, in a modern language. We work in .NET/C#; if you come from Java, Go, Python, TypeScript or Rust, we expect you to be willing to switch.
Daily, hands-on use of AI coding agents (Claude Code, Cursor, Copilot or similar), well beyond experimenting. You know how the context you give an agent shapes its output, and you can name a time you caught or rejected what it produced.
Must have: hands-on experience building with Claude or other AI tools. You've shipped at least one LLM-powered feature to real users, and you can explain how you measured its quality and what you changed when it went wrong.
Distributed systems experience: microservices, async and event-driven flows (Kafka or similar), databases, and cloud-native deployment.
Product sense. You have opinions about what to build and why, and you back them with data and user evidence. You're comfortable cutting scope to ship.
Full ownership. You own outcomes, not tasks. You take a feature from idea to production, handle the unglamorous details yourself, and stay accountable for how it works for customers after release.
Clear communication in English, written and spoken, in an international team.
Nice to have
Built agents or MCP servers, or tool-calling workflows with the Claude or OpenAI APIs.
Worked on LLM evaluation or keeping prompts and models versioned and tested.
Background in application security or developer tooling: SAST, SCA, secrets detection, CI/CD.
Built a B2B SaaS product used by engineering teams.
Experience with graph data (ArangoDB, GraphQL) or Terraform and Kubernetes.
Side projects or open source that show you build things because you want them to exist.
Shipped production UI in React and TypeScript, or another modern frontend framework.
Benefits
At On The Spot, we’re creating a workplace people would want to stay in: supportive, well-organized, and fair in terms of conditions and benefits.
We’ll share more about our benefit package during the interviews. In the meantime, you can always check our Glassdoor reviews.

Похожие заказы