Responsibilities

Model Strategy: Evaluate and select LLMs, balancing the trade-offs between cost, latency, reliability, and accuracy for specific tasks
Agent Architecture: Design prompt frameworks and agent behaviors for complex workflows including email generation, web research, and CRM integration
Workflow Optimization: Build and refine multi-step agent chains using RAG, web search, and tool-use (calendars, APIs, etc.)
Infrastructure & Safety: Drive choices for orchestration, persistent memory, and "eval loops" while building the guardrails that ensure AI safety and trust
Future Modalities: Explore and deploy emerging tech, from voice AI to multi-modal reasoning, to make our Artisans feel truly human-like

Basic qualifications

Experience: 2+ years of experience shipping production-grade AI products, either at an app-layer startup or on a foundation model team
Technical Depth: Deep hands-on experience with agents, function calling, RAG pipelines, or self-healing workflows (e.g., LangChain, ReAct, OpenAI Tools)
Prompt Engineering: Strong background in prompt design, chaining, and retrieval systems
Operational Excellence: Proven ability to own the latency, reliability, and cost of LLM-powered systems in a live environment
Communication: Excellent verbal and written communication skills with a penchant for directness and candor
Location: Based in San Francisco, New York, or Remote (USA)

Founder Mindset: We empower you to take initiative, challenge ideas, and push for 10x outcomes
Impact-Driven: We focus on the 80/20 rule—killing sunk costs quickly and focusing on what moves the needle for our customers
High Standards: We care about the details, from the elegance of the code to the quality of the product copy
No Drama: We maintain a "winning team energy"—low ego, high positive vibes, and a genuine love for building
Growth: Work at a fast-scaling startup ($35M+ raised) with a clear path to market leadership in the AI worker space

Used for matching and alerts on DevFound

Fulltime Remote Ai Ai Engineer Robotics