We are looking for a senior AI Engineer to put AI applications into real production, not just a prototype that impresses in a demo and breaks at scale.
You will design RAG pipelines, integrate models into existing systems, measure response quality with structured evals, and monitor cost and performance after go-live.
We expect someone who understands both software engineering and the specifics of language models, and who treats AI as a production system, with all the care that requires.
Put AI applications into production with measured quality and controlled cost.
Responsibilities
- Design and implement RAG pipelines and language model integrations.
- Integrate AI applications with existing systems, APIs, and databases.
- Define and run quality evaluations (evals) for AI-generated responses.
- Implement security guardrails and handling for model failure cases.
- Monitor cost, latency, and performance of AI applications in production.
- Collaborate with engineering and product on defining viable use cases.
- Critically assess the limitations and risks of each model or AI vendor used.
Requirements
- Solid software engineering experience, with recent focus on AI applications.
- Command of RAG, embeddings, vector databases, and LLM API integration.
- Knowledge of system architecture to safely integrate AI into existing products.
- Hands-on experience with cloud environments to host and scale AI applications.
- Rigor in evaluating AI response quality with structured evals, not just manual testing.
- Clear communication to explain AI limitations and risks to non-technical stakeholders.
Nice to have
- Experience with fine-tuning or model training.
- Background with multiple LLM providers (Anthropic, OpenAI, open source models).
- Knowledge of observability specific to AI applications.
- Experience with security guardrails and prompt injection prevention.
- Publications or open source contributions related to applied AI.
- Python
- LangChain
- OpenAI API
- Anthropic API
- Pinecone
- AWS
- Remote, flexible setup: you organize your routine around deliverables, not the clock.
- Growth budget for courses, certifications, and technical events.
- Health and wellness stipend.
- Real access to and ownership of the tools and AI stack we use in day-to-day engineering.
- Results-oriented culture: deliver well, and you get the autonomy to decide how and when you work.
- Small, senior squads with real room for technical decision-making.