Technical Staff Member – Agentic Engineer

Jobtailor; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Jobtailor is seeking an expert to design and build agentic systems and a deployment platform. You will own end-to-end contracts for skills and evaluations, and drive scalable orchestration across agents and evaluations.

You will collaborate with Applied Science to train models and refine the harness, delivering reliable systems for production environments and enabling discovery-driven product development.

Qualifications

• Must have shipped agentic systems in production with reliability focus.
• Proven track record building tools or frameworks for engineering teams.
• Proficient in designing and managing evaluation frameworks.
• Hands-on experience building MCP implementations.
• Experience managing prompts and skills in production environments.
• Familiar with authorization frameworks and best practices.
• Comfortable with product discovery.

Responsibilities

• Define and implement skill-and-eval contract end-to-end for one vertical.
• Build an opinionated platform for agent deployment and lifecycle management.
• Develop a high-throughput orchestration engine to manage agents and evaluations at scale.
• Work at the seam between surface UX, underlying operating map, and shared platform services.
• Partner with Applied Science to train models leveraging the harness.

Skills

Agentic systems

Engineering tools

Evaluation frameworks

MCP implementations

Prompts management

Authorization frameworks

Product discovery

Tools

Agent frameworks

Frontend (React/Next.js)

Job description

• Define and implement the skill-and-eval contract, running end-to-end for one real vertical.
• Build an opinionated platform for agent deployment and lifecycle management.
• Develop a high-throughput orchestration engine designed to manage agents and evaluations at scale.
• Work at the seam between the surface people use, the operating map underneath it, and the shared platform services below that.
• Partner closely with Applied Science, training their own models leveraging the harness.

Requirements

• Proven experience shipping agentic systems into production environments where reliability is critical.
• Demonstrated track record of building tools or frameworks for engineering teams.
• Proficiency in designing and managing evaluation frameworks.
• Hands-on experience building Model Context Protocol (MCP) implementations.
• Experience managing prompts and skills in production environments.
• Familiarity with authorization frameworks and best practices.
• Comfort and experience in product discovery.
• Nice-to-have skills include: Experience in insurance or another regulated operational domain; Learning from logged human decisions; Built internal tooling for agentic software development; Enough frontend range (React/Next.js); Contributions to open-source agent frameworks; Experience partnering with applied-science teams.

Core Competencies

Demonstrates expertise in building and managing agentic systems, with a focus on reliability and evaluation frameworks. Proficient in collaborating with applied science teams and developing tools for engineering efficiency.