Staff AI Engineer

Recruiting From Scratch•San Francisco, CA

1d•Onsite

About The Position

An early-stage AI startup is building AI agents to transform insurance business operations. The company develops agentic systems that reason through complex workflows, coordinate actions, use tools, evaluate outputs, and deliver reliable outcomes in real-world business environments. The Staff AI Engineer will lead the development of sophisticated AI agent systems, evaluation frameworks, and infrastructure for production agentic applications. The role focuses on application-layer engineering with existing large language models rather than training foundation models from scratch. The engineer will shape AI architecture, explore multi-agent systems, build orchestration infrastructure, and take AI products from initial exploration through production deployment. This is a hands-on technical leadership role that combines software engineering, practical AI agent experience, and zero-to-one product development in a startup setting. The position is fully onsite in San Francisco, five days per week, Monday through Friday. The role requires an undergraduate degree in Computer Science from a top-30 university and at least eight years of relevant technical experience.

Requirements

At least 8 years of software engineering, machine learning engineering, or closely related technical experience.
Staff-level engineering capability, including evidence of leading complex technical initiatives and influencing architecture.
Hands-on experience building AI agents.
Experience taking a B2B SaaS product or major product capability from zero to one at a startup.
Experience building and deploying AI-powered applications using existing LLMs.
Demonstrated ability to own projects from initial exploration through production deployment.
Experience working in an early-stage or high-growth startup where priorities evolve quickly.
Strong individual contribution skills alongside technical leadership and mentorship.
Undergraduate degree in Computer Science from a top-30 university.
Ability to work fully onsite in San Francisco five days per week.
Strong Python engineering skills and strong backend engineering capabilities.
Strong software engineering fundamentals, system design skills, and technical judgment.
Practical experience designing, implementing, and deploying AI agents and multi-step agent workflows that use tools.
Experience with agent orchestration, execution flows, context management, and tool-using systems.
Ability to build and maintain evaluation harnesses, test suites, or benchmarks for AI applications.
Experience evaluating agent behavior across realistic tasks and failure scenarios, designing repeatable experiments, and measuring improvements.
Understanding of feedback-driven improvement and methods for improving agent reasoning and task completion.
Experience building systems that use APIs and external services.
Ability to identify reliability issues in long-running or complex agent workflows.
Ability to translate experimental AI approaches into maintainable production software.
Ability to handle errors, retries, state, and recovery in complex workflows.
Strong understanding of testing, debugging, monitoring, and improving AI-powered systems.
Ability to operate with ambiguous requirements, balance prototyping with production-quality engineering, and make decisions with incomplete information.
Strong product sense and ability to connect technical work to customer needs.
Strong ownership, accountability, communication, collaboration, problem-solving, and execution-oriented judgment.
Ability to lead through technical expertise and implementation, mentor engineers, and improve team-wide engineering practices.
Focus on application-layer AI engineering rather than exclusively on model training or ML research.

Nice To Haves

Experience building multi-agent systems in production.
Experience developing MCP servers and tool integrations.
Experience with long-running agents and complex workflow orchestration.
Experience building evaluation frameworks for agentic applications.
Experience applying feedback-driven methods to improve agent performance.
Experience with AI applications in insurance or other complex, regulated business domains.
Experience establishing AI engineering practices at an early-stage startup.
Experience mentoring engineers and influencing technical strategy across a team.

Responsibilities

Design, build, and deploy sophisticated AI agents for complex insurance workflows using existing large language models.
Experiment with multi-agent architectures, reasoning strategies, and feedback-driven approaches to improve agent performance.
Build agents that execute multi-step tasks, use external tools, maintain context, and manage long-running workflows reliably.
Identify failure modes and improve the reliability, accuracy, and consistency of agent behavior.
Translate product requirements into practical AI architectures that can be deployed and maintained in production.
Build evaluation harnesses, datasets, test cases, and measurement frameworks for agent performance across realistic tasks and edge cases.
Create repeatable methods to compare prompts, agent architectures, model configurations, and orchestration strategies.
Use evaluation results to guide engineering decisions and measure performance against product and business outcomes.
Design and implement orchestration systems coordinating AI agents, tools, APIs, external services, and multi-step workflows.
Develop and integrate Model Context Protocol servers and other tool interfaces where appropriate.
Create reusable components for agent execution, context management, tool use, and workflow coordination.
Improve orchestration reliability with structured error handling, monitoring, retries, and recovery strategies.
Identify architectural bottlenecks and improve performance, scalability, and maintainability.
Take ownership of AI engineering initiatives from exploration through production deployment.
Prototype agent capabilities, validate their effectiveness, and turn successful experiments into production systems.
Work with product and engineering stakeholders to identify high-impact opportunities and translate ambiguous requirements into technical approaches and measurable outcomes.
Make architectural decisions that balance development speed, reliability, and long-term maintainability.
Establish engineering standards for building, testing, evaluating, and maintaining AI-powered systems.
Lead technical decisions involving agent architecture, orchestration, evaluation, and production deployment.
Mentor engineers, communicate technical tradeoffs, and help establish a repeatable approach to building reliable AI agent products.
Remain hands-on with implementation while influencing the broader technical direction.