🛠 Tech Stack

💼 About This Role

You'll design and build backend systems powering LLM-based agent workflows, including multi-step agent architectures and retrieval pipelines. You'll optimize accuracy, latency, and cost in production while developing evaluation frameworks and human-in-the-loop mechanisms. This role offers ownership of end-to-end systems in a fast-paced, AI-first environment.

🎯 What You'll Do

• Design and maintain backend systems for LLM-based agent workflows
• Develop and optimize LLM-powered systems for accuracy and reliability
• Build evaluation frameworks for agent performance and quality
• Collaborate with product teams to align technical decisions with customer needs

📋 Requirements

• 5+ years of software engineering experience with production backend systems
• Hands-on experience with LLM-powered systems including RAG or multi-agent workflows
• Strong proficiency in Python and backend engineering
• Experience with search and retrieval systems such as Elasticsearch or Pinecone

✨ Nice to Have

• Experience with multi-agent systems
• ML fundamentals (precision/recall, bias-variance tradeoffs)
• Open-source AI contributions

🎁 Benefits & Perks

• 💰 Competitive compensation with equity/stock options
• 🏥 Comprehensive health and dental coverage from day one
• 🏖️ Unlimited vacation policy with trust and autonomy
• 🖥️ Modern tooling including Mac or PC equipment
• 📈 Career growth opportunities with leadership exposure

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Screen· 30 min
2. 2Technical Interview· 60 min
3. 3On-site Interview· 4 hours