🛠 Tech Stack

💼 About This Role

You'll be the third Applied AI engineer, pushing boundaries of AI employees. You'll shape product direction and optimize multi-step agent chains. This role offers hands-on work with state-of-the-art LLMs.

🎯 What You'll Do

• Evaluate and select LLMs balancing cost, latency, reliability, and accuracy.
• Architect prompt frameworks and agent behaviors for core workflows.
• Optimize agent chains using RAG, web search, and tool integrations.
• Build safety, trust, and controls into agent systems.

📋 Requirements

• 2+ years shipping AI products in production.
• Deep experience with agents, function calling, or RAG pipelines.
• Strong background in prompt design, chaining, and retrieval systems.
• Experience owning latency, reliability, and cost of LLM systems.

✨ Nice to Have

• Experience with OpenAI RAG + web search tools.
• Ability to explore novel techniques and ship quickly.

🎁 Benefits & Perks

• 💰 Competitive compensation
• 🏖️ Remote flexibility
• 📈 High impact role

📨 Hiring Process

Intro call, CEO interview (15 min), take-home assignment, CPTO review, culture interview with CEO.