Founding AI Engineer

San Francisco, California

Development - Back End

Permanent

Our client, an AI-driven legal tech company, is hiring a Founding AI Engineer to join the team in San Francisco, CA. The successful candidate will design and deploy production-grade LLM systems for a next-generation legal technology platform, while also transforming complex legal workflows into reliable, agent-driven solutions that work seamlessly across documents, communications and structured data.

Responsibilities

Build and deploy production-grade LLM systems for document analysis, legal drafting and workflow automation.
Design and orchestrate AI agents that execute complex, multi-step tasks using frameworks such as LangChain and Deep Agents.
Create comprehensive AI evaluation frameworks to measure accuracy, reliability, regressions and production performance.
Build scalable pipelines for ingesting, processing and structuring complex documents, including OCR and unstructured data extraction.
Improve model and agent performance through prompt engineering, retrieval optimization, context management and tool integration.
Develop RAG, memory and retrieval systems that allow AI agents to reason effectively across large volumes of legal information.
Monitor, troubleshoot and improve long-running agent workflows, identifying and resolving reliability issues and production failures.
Partner with product and engineering teams to turn complex legal processes into scalable AI-powered workflows and product capabilities.
Help shape the wider AI architecture, making practical technical decisions as the platform and customer base grow.
Own AI systems throughout their lifecycle, from experimentation and evaluation to production deployment, monitoring and continuous improvement.

Skillset

At least 3 years of professional software engineering experience, successfully building and shipping production AI systems.
Strong proficiency in TypeScript, with a solid background in developing reliable, production-grade backend services.
Hands-on experience building with LLMs, AI agents and agent orchestration frameworks, ideally including LangChain or similar technologies.
Experience developing AI evaluation and testing frameworks, including benchmarks, test datasets, regression testing and performance monitoring.
Strong knowledge of RAG, prompt engineering, context engineering and tool-enabled LLM architectures.
Experience with document intelligence, OCR, information extraction and unstructured data processing.
Proven ability to diagnose and improve the reliability, accuracy and performance of production AI systems.
A high-ownership approach, with the ability to take complex technical systems from initial concept through to production.
Experience within an early-stage startup or similarly high-growth engineering environment would be highly valued.