AI Engineer

Role overview Develop AI-powered product features that provide useful, context-aware insights and support collaboration. The work combines retrieval and generation pipelines with backend APIs, product experimentation, evaluation, and deployment, with ownership across data, service, and user experience layers.

Responsibilities - Design data preprocessing, embedding, and retrieval pipelines for relevant context across sessions or product workflows. - Build and improve retrieval-augmented generation systems using language models and retrieval tools. - Develop Node.js and Python APIs that deliver AI-generated insights to React applications. - Partner with product, design, and data colleagues to shape features and refine them based on user needs. - Prototype and deploy experiments using existing AI platforms, then measure model quality with benchmarks, regression checks, and ongoing evaluation. - Work with infrastructure and data teams to deploy and scale services in cloud environments.

Requirements - At least two years of experience in AI engineering, applied machine learning, or full-stack development focused on LLM systems. - Familiarity with RAG, vector search, prompt and context engineering, and fine-tuning workflows. - Ability to experiment with emerging AI tools and turn prototypes into useful delivered features. - Experience connecting data, backend, and frontend components into a cohesive user-facing capability. - Collaborative, product-oriented approach to solving user problems with data-informed features.

Nice to have - Familiarity with tools and platforms in the described stack, including Node.js, Python, React, MongoDB, ClickHouse, Supabase, Kafka, Docker, and CI/CD. - Experience with OpenAI, Anthropic, or Gemini models, and cloud deployment such as Fly.io.