At Imperum, we're building an agentic AI platform for security operations — an autonomous SOC that detects, investigates, contains, and remediates threats with minimal human intervention. Our product isn't "AI-assisted" security; it's a system of AI agents that run the SOC loop end-to-end, from alert triage to incident response and forensic analysis.
We're looking for a senior full-stack engineer who is fluent in agentic AI and uses AI coding tools as a core part of their own development loop. You'll ship features across the whole platform, own the quality of everything that lands in main, and help shape how our team builds with AI. A security-operations background is a strong plus — and if you don't have it yet but you're genuinely excited to go deep into SOC, IR, and forensics, we'll invest in getting you there fast.
⚡ What you'll do
• Build and ship full-stack features across frontend, backend, APIs, and the data layer — using AI coding tools as your primary force multiplier.
• Translate product requirements into clear specs, plans, and prompts that AI agents can execute reliably — and iterate until the output is production-grade.
• Own the quality bar: review, refactor, and harden AI-generated code. You're the engineer of record for everything that lands in main.
• Design and evolve our architecture and conventions docs (agent context, coding standards, project rules) so AI assistants consistently produce code that fits our codebase.
• Integrate AI into the day-to-day: scaffolding, test generation, refactors, migrations, code review, and documentation.
• Work with MCP servers, custom tools, and internal agents to automate engineering tasks and extend what our AI assistants can do.
• Contribute to observability, CI/CD, and deployment pipelines so AI-authored changes ship safely and roll back easily — across both cloud and on-prem / air-gapped deployments.
• Pair with product, design, and other engineers to ship end-to-end. AI is a teammate, not a replacement for collaboration.
✅ Must-have
• EU nationality, or an existing right to work in the EU without sponsorship (we can't sponsor visas or relocation from outside the EU for this role).
• 5+ years of professional full-stack experience shipping production software.
• Strong hands-on Python (backend) and TypeScript / React (we run Next.js on the frontend) — comfortable across the stack.
• Agentic AI as core knowledge: you've built or shipped features powered by LLM agents, not just called a chat API. Comfortable with tool use / function calling, multi-step planning and multi-agent orchestration, RAG, MCP, evaluations, guardrails, and the failure modes of autonomous agents (hallucinations, loops, prompt injection, unsafe tool calls).
• Hands-on, regular use of AI coding assistants (Claude Code, Cursor, Copilot, Windsurf, Aider, or equivalent) on real projects — not just demos.
• Strong prompt and context engineering: you scope tasks, feed the right context, and iterate with AI agents to get reliable results.
• A critical eye for AI output: you spot hallucinated APIs, subtle bugs, insecure patterns, and over-engineered code — and fix them fast.
• Working knowledge of relational and/or document databases (PostgreSQL or similar) and basic data modeling.
• Comfortable with self-hosted / on-prem / Docker-based deployments, not just managed cloud (we ship both in the cloud and fully air-gapped on customer premises).
• Git, code review, testing, and CI/CD as non-negotiable practices.
• Fluent English, spoken and written — our working language across code, docs, meetings, and async.
• Able to work remotely with meaningful overlap with Central European Time (CET).
➕ Strong plus
• Security operations background — SOC, Incident Response, Forensics. A plus, not a gate: SIEM rules, EDR telemetry, MITRE ATT&CK, the IR lifecycle, and forensic fundamentals (chain of custody, host/network/memory artifacts, timeline analysis). Don't have it yet but eager to go deep? Tell us — we'll invest in you.
• Search / streaming / workflow infra we run at the core: OpenSearch (or Elastic), Kafka, Temporal.
• Knowledge graphs / GraphRAG for agent context.
💡 Nice-to-have
• Security tooling: SIEM (Splunk, Elastic, Sentinel), EDR/XDR, SOAR, threat intel, or detection engineering.
• Docker/Kubernetes at scale.
• Certs or hands-on security background (GCIH, GCFA, OSCP, CEH, Blue Team labs), or contributions to detection rules, IR playbooks, or threat research.
• DevOps / platform: IaC, observability, security hardening.
• Open-source, technical writing, or sharing how you work with AI tools.
🚀 Our cadence: idea to release in 5 days
We run a strict 5-day delivery cycle — greenlit idea to production in one working week. No exceptions, no quietly sliding deadlines. This is only possible because AI coding tools are deeply embedded in how we build. Security-critical paths still get the rigor they demand — speed never means cutting corners on safety.
• Day 1 — Spec & shape: scope, write the spec + agent context, break work into agent-executable tasks.
• Days 2-3 — Build: implement end-to-end with AI agents. Tests alongside the code, not after.
• Day 4 — Harden: review AI-generated code in depth, refactor, tighten security and observability, run against real data and edge cases.
• Day 5 — Ship: deploy, monitor, document, close the loop. What doesn't fit is cut or descoped — not delayed.
If shipping a meaningful feature every week sounds energizing rather than terrifying, you'll fit right in.
🤝 How we work
• Stack: Python backend, TypeScript / React (Next.js) frontend.
• AI-first, not AI-only: every engineer is accountable for the code that ships. AI accelerates us; it doesn't excuse us.
• Small, senior team. Short feedback loops. High autonomy and ownership.
• We invest in tooling: prompt libraries, shared conventions, custom MCP servers, internal agents.
• We pay for the best AI tools and models.
• Async-friendly, remote-first, with in-person time when it matters.
🎁 What we offer
• Competitive base + RSUs.
• Top-tier hardware and a budget for AI tools, courses, and conferences.
• Flexible remote or hybrid setup.
• A team that treats AI-assisted engineering as a craft worth mastering.
📩 How to apply
Send your CV, your GitHub or portfolio, and a short note on how you use AI coding tools day-to-day. Got a favorite prompt, workflow, or war story about shipping something non-trivial with an AI agent? We want to hear it.
#Hiring #AIEngineering #FullStack #Python #React #AgenticAI #SecOps #RemoteEU