Applied AI Engineer (LLM) — 6-Month Contract

Role overview Build production AI features that help businesses use their own data, including retrieval systems, assistants, and agentic workflows. The work spans implementation, evaluation, safety controls, and performance, with human review built into consequential decisions.

Responsibilities - Design and ship LLM-powered features grounded in real or private data. - Create evaluation methods and guardrails to check output quality and reduce failure risks. - Define where human oversight is needed and prevent models from taking irreversible actions alone. - Monitor and improve latency, operating cost, and response quality. - Work with product and customer stakeholders to assess where AI is useful and explain its limits.

Requirements - At least four years of software engineering experience, including shipped work using LLMs or machine-learning APIs. - Strong Python and/or TypeScript skills and familiarity with current AI tools. - A skeptical, practical approach to model output and experience building checks for likely failure modes. - Ability to become productive quickly and explain AI capabilities and limitations to nontechnical stakeholders.

Nice to have - Experience with retrieval, vector search, or grounding models in private data. - Familiarity with prompt evaluation, fine-tuning, or safe agentic systems. - A side project or demo that shows an AI idea developed into a usable product.

Benefits and work setup - Six-month remote contract, with potential to extend; suitable for EU or Americas time zones, with shared working hours and async collaboration. - Hardware and API/compute budget provided for the engagement.