Applied AI Engineer

Role overview

Improve AI powered product experiences by making third party model APIs more accurate, responsive, and useful to customers. The focus is applied engineering rather than training foundation models: you will develop prompts, evaluation systems, and product integrations, with particular relevance to voice interactions.

Responsibilities

- Improve the quality of model outputs through systematic prompt development and iteration. - Build evaluation pipelines that measure AI behavior and help track quality across changes. - Assess new models with evaluations and use measured results to inform product choices. - Integrate LLM APIs into software experiences, balancing response quality, token usage, and latency. - Apply AI capabilities to practical customer workflows where usefulness matters more than experimentation for its own sake.

Requirements

- At least three years of software engineering experience. - Hands on experience with LLM APIs such as OpenAI or Anthropic. - Strong prompt engineering skills and a methodical approach to improving outputs. - Experience building evaluation pipelines for AI systems. - Proficiency in TypeScript or Python. - A strong focus on measuring quality and making it better over time.

Nice to have

- Voice AI experience with tools such as Deepgram, ElevenLabs, or Whisper. - Experience reducing AI costs at scale, or a background in NLP or conversational AI. - Familiarity with model fine tuning.

Benefits and work setup

- Remote work across Europe or the United States. - Competitive salary based on location and experience. - Equity of 0.8%–1.2%, vesting over four years with a one year cliff.