Head of AI Engineering

Location: LA/SF/NY Preferred
Type: Full-time

About Inhouse

Inhouse is the #1 AI lawyer for small to midsize businesses. We combine AI, our own law firm, and an expert feedback loop to deliver fast, compliant, high-quality legal work at a fraction of the cost and turnaround time of traditional firms. We grew revenue 1,500% last year and recently raised a $5M seed round from leading VCs and the former CEO & Cofounder of LegalZoom.

About the Role

General-purpose LLMs are not reliable at high-stakes legal work. We are building expert-in-the-loop AI systems that continuously improve through lawyer feedback, strong retrieval, structured evaluation, and production-grade engineering.

We are looking for an engineering leader to take ownership of the vision and development of agentic AI at Inhouse. This is a hands-on technical leadership role for someone who has already built and shipped agentic AI systems in production, can own architecture and delivery, and can set the engineering standard for how this work gets done.

You will work directly with lawyers to translate legal workflows into reliable AI systems. You will also serve as a team lead and play a critical role in hiring, managing and scaling the AI engineering team.

What You'll Do

• Architect expert feedback loop, agents and knowledge base
  • Develop an agent architecture with a knowledge base which can be used to dynamically insert expert feedback based on user context.
  • Determine the process to convert feedback from our legal team’s daily operations into knowledge base updates which can rapidly improve agent performance.
  • Build evaluation infrastructure - including LLM-as-a-judge evals, feedback capture and regression testing.
  • Establish best practices for prompt and workflow versioning, testing, logging, deployment, and incident response for AI systems (should be durable and LLM agnostic)
• Build agentic abilities to auto capture user context while minimizing user effort (eg using web search, integrations like email, google drive)
• Build features so the agents get smarter with usage, driving high retention (eg enhanced memory, task continuation)
• Stay on the frontier of both AI and legal AI

What We're Looking For

Required

• 7+ years of production backend engineering experience in Python - you will write code that ships and scales.
• 2+ years tech lead experience: you've owned architecture decisions, led development, handled deployment and monitoring
• 1+ year building LLM-based agents in production, particularly:
  • Built architectures with tool calls and subagents
  • Built context management and memory for agentic systems
  • Built LLM-as-a-judge or similar evaluation frameworks
  • Built expert-in-the-loop systems where domain experts continuously improve accuracy
  • Wrote system prompts or managed the team which did that
• Experience working in an AI-native development manner using tools such as Claude Code, Cursor, Codex, or similar
• Worked in startup environment with high ambiguity, urgency, and ownership

Preferred

• Experience building planning-based agents — systems that reason about goals, decompose tasks, and decide on actions autonomously
• Experience with frontend or workflow UI development sufficient to collaborate effectively across the product stack
• Experience with hiring and managing engineering teams

Compensation & Benefits

• Competitive salary and meaningful founding engineer level equity
• Unlimited PTO
• High impact work: Build the AI at the center of the largest and fastest growing legal AI product
• Fully covered health, dental, and vision.

Inhouse is an equal opportunity employer. We value diversity and are committed to creating an inclusive environment for all employees. We consider qualified applicants with arrest and conviction records in accordance with the San Francisco Fair Chance Ordinance.