🛠 Tech Stack

💼 About This Role

You'll design, build, and deploy production-grade AI agents for enterprise customers at scale, using Large Language Models to solve real-world business problems. You'll own the full lifecycle from prototype to production, ensuring agents are reliable, observable, and auditable. This role combines customer-facing impact with deep technical work on frontier AI systems.

🎯 What You'll Do

• Translate business problems into agentic workflows with clear success criteria.
• Lead design, build, and delivery of LLM-powered agents with enterprise reliability.
• Define evaluation standards to measure success, failures, and regressions.
• Debug agent behavior and improve prompts, workflows, tools, and guardrails.

📋 Requirements

• Production-grade software system building and shipping experience.
• Hands-on experience designing, building, and evaluating LLM-based agents in real-world applications.
• Deep familiarity with modern LLM ecosystems including GPT, Claude, Gemini, vector databases, RAG, and agent frameworks.
• Strong proficiency in Python and/or JavaScript/TypeScript.

✨ Nice to Have

• Experience working directly with customers on LLM-powered solutions.
• Technical leadership guiding architecture and delivery of complex AI systems.

🎁 Benefits & Perks

• 🏖️ 30 working days of vacation
• 💻 Work with a team on cutting-edge AI research
• 🍽 Weekly lunch stipend and in-office meals
• 🦷 Full health and dental benefits with mental health budget
• 🐣 100% Parental Leave top-up for up to 6 months