About the Role

• This is a rare opportunity to build AI products at the frontier of what’s possible.
• Your work will directly shape the next generation of autonomous, human-like AI employees that will interact with tens of millions of people every day.
• Applied AI isn’t a side project; it is the product.
• You’ll evaluate and integrate advancements across LLMs, retrieval-augmented generation (RAG), web search pipelines, voice AI, talking head avatars, multi-modal reasoning, and beyond.
• You’ll make Artisans more autonomous, reliable, and human in how they work.

Responsibilities

• Evaluating LLMs, choosing the right models balancing cost, latency, reliability, and accuracy.
• Architecting prompt frameworks and agent behaviors for Ava’s core workflows: email generation, chat interaction, meeting scheduling, prospect research, and more.
• Optimizing multi-step agent chains using RAG, web search integrations, and tool use (e.g., CRMs, calendars, APIs).
• Driving infrastructure choices for routing, orchestration, eval loops, and persistent memory across agents.
• Building safety, trust, and controls into agents, partnering with product to design user guardrails, fail-safes, and success metrics.
• Exploring and deploying emerging modalities from voice AI and talking head technology to multi-modal reasoning to make Ava more human-like.
• Designing agent workflows for strategic decisions, self-optimization, adaptation, and autonomous measurable outcomes.

Requirements

• 2+ years shipping real AI products in production, at an AI startup or foundation model team.
• Experience with agents, function calling, RAG pipelines, or self-healing workflows (LangChain, ReAct, Dust, OpenAI Tools, etc).
• Strong background in prompt design, chaining, and retrieval systems; experience with OpenAI’s RAG/web search tools is a major plus.
• Experience managing latency, reliability, and cost of LLM-powered production systems.
• Ability to think like a researcher but ship like an engineer, applying novel techniques quickly.
• Excellent communication skills.

Why Join Us

• Build category-defining AI employees impacting tens of millions.
• Work directly with the CEO on core product direction.
• Extremely competitive compensation with meaningful equity and full benefits.
• Autonomy to shape applied AI practices and your team from the ground up.
• Join a fast-moving, mission-driven culture shipping meaningful work weekly.
• Be on the cutting edge of AI research and application, transforming papers into products rapidly.

Details

• Role: Engineering
• Engineering type: Machine learning
• Job type: Full-time
• Experience: 3+ years
• Location: San Francisco or NYC (in-person)
• Remote: No
• US visas: Will sponsor