Leads the team this role joins
Hires for this team
On the team, can refer you
From your own Gmail and LinkedIn.
How this role compares
One of 46 open AI Engineer roles we are tracking today.
Posted 9 days ago, with 12 of the others posted since and 33 still open from before.
Counted across the roles Frontrunner has open right now.
About the role
This is a remote, full-time AI Engineer role for a strong middle to senior engineer with at least 4 years of backend or full-stack experience. The engineer owns the quality and reliability of AI features in production, from delivery through evaluation. Candidates may live in any country within about 4 hours of Central European Time, and the listing tags Ukraine, Moldova and several other countries.
What you’ll do
- Take ownership of major AI features and LLM workflows and deliver them on schedule.
- Keep structured output consistent across different LLMs for the same type of request.
- Integrate multiple LLM providers through an AI gateway, handling model selection, fallback and cost.
- Design tool-using and agentic workflows, including MCP-based tools and function calling.
- Build multi-step LLM workflows and RAG pipelines covering indexing, embeddings, retrieval and re-ranking.
- Manage prompts with dynamic context and conditional logic.
- Run A/B tests across models and prompts, and report their impact.
- Debug LLM chains with traces to reduce latency, cost and hallucinations.
- Write TypeScript across Node.js and Cloudflare Workers, with tests for validation and fallback paths.
- Monitor AI metrics, resolve production issues and document root causes and architecture decisions.
What they’re looking for
- 4+ years of backend or full-stack experience, with production TypeScript and Node.js.
- 1+ year of AI or LLM systems in production with real users.
- Daily use of AI development tools such as Claude Code or Cursor.
- Hands-on production work with LLM APIs from providers such as OpenAI, Anthropic or Google Gemini, including structured output, function calling, streaming and cost control.
- Experience with agentic AI or RAG pipelines.
- Experience with LLM observability and evaluation tools such as Langfuse or LangSmith.
- Experience with AI gateways and model routing such as OpenRouter or Cloudflare AI Gateway.
- Solid knowledge of PostgreSQL and caching with Redis, KV or similar.
- Strong ownership of engineering quality and delivery.
Nice to have
- Evaluation frameworks such as LLM-as-a-judge and RAGAS.
- MCP servers, clients or tool contracts.
- Cloudflare Workers services such as KV, Durable Objects, Queues, R2 and Containers.
- OpenSearch, Elasticsearch or pgvector.
- Workflow engines such as Hatchet, Temporal or Inngest.
- Browser automation with Playwright, CDP or browser-use.
- Fine-tuning for strict schema compliance.
- Python for evaluation scripts and AI tooling.
What’s on offer
- Remote work with flexible hours.
- Unlimited PTO.
- Paid national holidays.
- A company-provided MacBook for employees who need one.
- An independent contractor agreement with flexibility and tax considerations.
Skills
Questions about this role
Is this role remote?
Yes, it is remote, with working hours aligned to the CET zone.
How many years of experience do I need?
4+ years of backend or full-stack engineering, plus 1+ year of production LLM work.
What is the interview process?
A recruiter screen (40 minutes), a technical interview (90 minutes) and a final interview (60 minutes).
Is it full-time?
The listing is tagged full-time and offers an independent contractor agreement.