AI Engineer

Role overview Build and operate AI features powered by large language models, from retrieval and agent workflows through evaluation and production serving. The work spans engineering and product collaboration, with an emphasis on measuring quality, latency, and cost as features reach users.

Responsibilities - Develop LLM features such as retrieval-augmented generation, tool-using agents, structured extraction, and multi-step workflows. - Create evaluation datasets and automated checks to track model quality and catch regressions. - Tune prompts and route requests across model providers to balance response quality, speed, and cost. - Build embedding and vector-search pipelines, including chunking, hybrid retrieval, and reranking. - Improve serving reliability with streaming, retries, fallbacks, caching, rate limits, and observability. - Work with product and design to shape, ship, and measure features; review code and support teammates.

Requirements - At least three years of professional software engineering experience, including one year building production applications with LLMs. - Strong Python and/or TypeScript skills, with experience across APIs, queues, databases, and cloud deployment. - Practical experience with RAG, embeddings, and vector databases, and sound judgment about when to use retrieval, prompting, or fine-tuning. - Experience evaluating model outputs with evaluation sets or equivalent systematic methods. - Familiarity with LLM APIs and tooling, including function calling, streaming, and structured outputs. - Clear written communication, product awareness, and ownership of a shipped AI feature. - Ability to overlap at least four hours per day with US Eastern or Central European time.

Nice to have Fine-tuning or LoRA, inference optimization, PostgreSQL/pgvector at scale, or experience in an early-stage startup.

Benefits and work setup Remote work across US and European time zones, flexible hours, and an async-first approach. The package includes salary and equity, paid time off, a learning and AI tooling budget, and a home-office and equipment stipend.