AI Application Engineer

You will translate state-of-the-art AI research into production-ready features, design and run experiments to validate approaches, and ship AI-powered product releases. You will build and maintain experimentation infrastructure, integrate AI tooling into engineering workflows, and optimize model deployment and inference. You will collaborate with engineers and stakeholders to turn research ideas into measurable product improvements and share findings to raise team capability in AI evaluation and context engineering.

Responsibilities

• Identify and prioritize high-potential AI experiments.
• Design and run experiments combining AI evaluations with A/B testing.
• Build and maintain experimentation infrastructure for scalable AI evaluations.
• Translate research into production features and drive product releases.
• Integrate AI tooling into engineering workflows to accelerate adoption.
• Disseminate research findings and build team capability in AI evaluations and context engineering.

Requirements

• Deep familiarity with AI evaluations, reasoning systems, agentic architectures, and context engineering techniques.
• At least 5 years of engineering experience.
• Exceptional programming skills and AI-first workflows.
• Experience with experiment design, A/B testing, and statistical analysis.
• Working knowledge of model deployment, inference optimization, and scaling.
• Proficiency with API integrations across multiple LLM providers, including OpenAI, Anthropic, Google, and open-source models.
• Demonstrated track record of shipping AI-driven product features.
• Experience working in remote, fast-paced, iterative development environments.

Benefits

• Equity
• Competitive benefits
• Fully remote work
• Work with a small passionate team
• Entrepreneurial opportunity with outsized impact
• Contribute to projects at the forefront of the web