We're building AI employees. Not chatbots. Not copilots. Autonomous digital workers that do real jobs.
Our first, Ava, is an AI BDR used by hundreds of companies. She researches leads, writes and sends emails in a customer's voice, runs multi-step outbound sequences, manages her own deliverability infrastructure, self-optimizes over time, and handles objections and meeting booking. She's not a tool someone uses. She's a teammate.
We're a YC W24 company, have raised $35M+ from investors including Y Combinator, and are at $8M+ ARR. Right now we're building Ava 2.0, a step change in what an AI employee can do. The engineering problems are hard and the surface area is enormous.
You'll be the third Applied AI engineer on the Artisan team! We're pushing the boundaries of what's possible with AI employees, and you'll play a key role in our product direction.
Evaluating LLMs, choosing the right models for the right tasks, 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 retrieval-augmented generation (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 - and figuring out how they make Ava more human-like
Designing agent workflows that make strategic decisions, self-optimize and adapt in real time, and deliver measurable outcomes autonomously
Location: San Francisco, New York, or Remote USA
Team: AI
Reports to: CPTO, Sam Stallings
2+ years shipping real AI products in production - either at an app-layer AI startup or on a foundation model team
Deep hands-on 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 or equivalents is a major plus)
Experience owning latency, reliability, and cost of LLM-powered systems in production
Ability to think like a researcher but ship like an engineer, exploring novel techniques and getting them into users’ hands quickly
Excellent communication skills
Introductory chat with our recruiter
15-minute interview with Jaspar, our CEO
Take home assignment
30-minute take home assignment review with Sam, our CPTO
30-minute culture and values interview with Jaspar, our CEO
Founder mindset. Everyone acts like an owner: take initiative, think big, challenge ideas, and push for 10× outcomes
Obsessed with impact. We apply the 80/20 rule, kill sunk costs quickly, and focus on what actually moves the needle
Customer-first, always. Every decision is made with the customer experience at the center
High standards, every detail. Quality matters in everything we ship, from product and code to copy and design
Clear, direct communication. We value candor, fast responses, and feedback
Winning team energy. We bring positive vibes, low ego, zero drama, and genuinely enjoy building together