At a Glance
- Tasks: Join a dynamic team to develop AI-driven software and enhance innovative scoring engines.
- Company: AMPD, a cutting-edge tech company focused on agent-augmented engineering.
- Benefits: Competitive salary, equity options, and flexible remote work.
- Other info: Work asynchronously with a small, high-performing team and enjoy excellent career growth.
- Why this job: Be at the forefront of AI technology and make a real impact in the industry.
- Qualifications: 5+ years in TypeScript/Node.js with experience in agentic coding.
The predicted salary is between 70000 - 90000 £ per year.
Why we're hiring
AMPD is shipping at speed (~800 commits / month, 13 PRs merged today alone) on a small team currently driving all engineering decisions, with Claude Code agents drafting and reviewing PRs in worktrees. We need a senior engineer who can plug into this workflow on day one, not someone who needs to learn agentic tooling from scratch.
How we actually work (read this first, it's the most important section)
We are an agent-augmented team. Engineering is a human + Claude Code partnership, not a human-only job. Specifically: Telegram is the ops surface. The AMPD OPS group chat is where bugs are reported, audits are run, deploys are announced, and decisions get made.
- Claude Code reads/writes Telegram via plugin. You'll be expected to participate in this channel, directing agents, reviewing screenshots from CEO, and dispatching fixes.
- Claude Code (or equivalent agentic CLI) is your IDE. Most non-trivial work runs through worktree-isolated background agents. You scope an issue, dispatch an agent in an isolated git worktree, the agent drafts a PR, you (or Claude Code itself, under merge-authority gates) review and ship.
- We have 31+ active worktree agents in the repo at any time, managing parallelism without stepping on each other is a core skill.
Skills + plugins:
- We use Claude Code skills (e.g. /triage-labels, /grill-with-docs) and MCP plugins (Telegram, GitHub). You should know how to author and consume them.
- GitOps everywhere. Push to main → CI builds → ArgoCD auto-promotes through dev → stage → prod (Hetzner k3s, prod is ampdaxo.com). Manual prod intervention should be rare.
- No-synthetics rule. AMPD's core promise: real data or empty state, never fabricated. If you write a heuristic fallback, it must be removed before shipping.
- Surgical-edits rule. No speculative abstractions, no opportunistic refactors. Touch only what the task requires.
The codebase you'll work in:
- Backend: Express.js + TypeScript strict, ~140 source files, 65 services, 13 route files, ~1930 Jest tests. Prisma + PostgreSQL (16 models, all CUID, cascade-on-delete). 6 LLM providers (OpenAI, Anthropic, Perplexity, Gemini, Groq, OpenRouter) wired through provider adapters with caching and rate-limiting.
- Frontend: Next.js 14 App Router + TypeScript strict, ~313 source files, NextAuth v4 (JWT), Playwright E2E, vitest unit. Tailwind + shadcn/ui.
- Infra: k3s on Hetzner, ArgoCD, GitHub Actions (build-only, local pre-push hook runs lint/build/test), Sentry, Airwallex billing.
Velocity: ~800 commits / 30 days. Small team, high cadence.
Architecture details: docs/ARCHITECTURE.md. Agent workflow: docs/agents/. Domain ADRs: docs/adr/.
What you'll own:
- GEO/AEO scoring engine. AMPD's three proprietary metrics (CPS, CFI, SAV) plus E-E-A-T, Topic Authority, Semantic Relevance, Content Freshness analysers. You'll improve and extend these.
- AI provider integrations. Adding new platforms, tightening prompts, managing rate limits and Groq credits.
- Audit pipeline. End-to-end from POST /api/scoring through provider calls → metric derivation → AnalysisDerivedMetrics row → dashboard render. Real production data, real money on the line. Trust + transparency. When the dashboard shows a number, that number must be defensible. You'll audit your own work the way the CEO audits ours.
What we need from you:
- Required: 5+ years backend or full-stack TypeScript / Node.js shipping production systems. Demonstrated agentic coding experience in Claude Code, Cursor, Aider, or similar.
AI-Native Engineer employer: AMPD
At AMPD, we pride ourselves on being an innovative and agile employer that fosters a collaborative work culture where human and AI partnerships thrive. Our remote, async-first environment allows for flexibility while ensuring that our engineers are at the forefront of cutting-edge technology, with ample opportunities for professional growth and meaningful contributions to impactful projects. Join us to be part of a small, dynamic team that values trust, transparency, and real data in every aspect of our work.
StudySmarter Expert Advice🤫
We think this is how you could land AI-Native Engineer
✨Tip Number 1
Get familiar with the tools we use! Since we're all about that agent-augmented workflow, dive into Claude Code and get comfy with Telegram. The more you know about how we operate, the better you'll fit in from day one.
✨Tip Number 2
Show us your skills in action! When you're applying, highlight your experience with multi-agent workflows and how you've managed worktrees. We want to see real examples of you dispatching agents and reviewing PRs, so don't hold back!
✨Tip Number 3
Communication is key! Since you'll be directing agents and writing issues, make sure your written communication is top-notch. Clear prompts lead to clear PRs, so practice crafting concise and effective messages.
✨Tip Number 4
Apply through our website! We love seeing applications that stand out, so make sure to follow the instructions carefully. Share your most interesting projects and a link to a PR that showcases your agent-driven work. We read everything, so make it count!
We think you need these skills to ace AI-Native Engineer
Some tips for your application 🫡
Be Yourself:When you're writing your application, let your personality shine through! We want to get to know the real you, so don't be afraid to show your passion for agent-driven engineering and how you fit into our team.
Tailor Your CV:Make sure your CV highlights your experience with TypeScript, Node.js, and any agentic coding you've done. We love seeing specific examples of your work, especially those that demonstrate your ability to manage multi-agent workflows.
Showcase Your Projects:In your application, include a brief note about your most interesting agent-driven project. This is your chance to impress us with your creativity and problem-solving skills, so make it count!
Follow Our Instructions:We appreciate attention to detail, so make sure you follow the application instructions closely. Send your email to hello@ampdaxo.com with all the required info, and remember, no bots or form letters – we want to hear from you directly!
How to prepare for a job interview at AMPD
✨Know Your Tools Inside Out
Before the interview, make sure you're well-versed in Claude Code and any other agentic tools mentioned in the job description. Familiarise yourself with how to dispatch agents, manage worktrees, and review PRs. This will show that you can hit the ground running.
✨Master the Communication Channels
Since Telegram is a key part of their operations, practice using it effectively. Be ready to discuss how you would report bugs, direct agents, and communicate decisions clearly. Good written communication is crucial, so brush up on your skills here.
✨Showcase Your Experience with Real Examples
Prepare specific examples from your past work that demonstrate your experience with multi-agent workflows and GitOps. Be ready to explain how you managed parallel tasks and resolved conflicts under pressure, as this will be a big part of the role.
✨Understand Their Metrics and Domain
Familiarise yourself with the GEO/AEO scoring engine and the proprietary metrics they use. Showing a genuine interest in how brands win on platforms like ChatGPT or Claude will set you apart. Be prepared to discuss how you can contribute to improving these metrics.
