Full-Stack Engineer

The client is hiring a Full-Stack Engineer to own the product experiences and agent infrastructure that make the agent improvement loop clear and actionable for engineering teams. You will talk to customers, decide what to build, build it and iterate until it is great, across the data layer, the UI, agent-swarm interfaces, verification platforms and the SDK. About 30% of the role is customer-facing., * Shape how the Judgment Agent runs large parallel investigations across thousands of production traces and merges findings into one actionable answer.

• Build the platform for verifying agent changes: hosted simulated environments, trajectory replay and monitors for unintended behavior.
• Make long agent traces, tool calls and failures understandable in minutes.
• Build the swarm UX for watching and redirecting parallel investigations.
• Own the improvement loop that turns production trajectories into datasets, judges and regression checks.
• Build the SDK and terminal-first experience, and platform infrastructure such as workspaces, roles, permissions, billing and limits.

Artificial Intelligence (AI) Agents, Team Lead/Manager, Customer Relations, User Interface/Experience (UI/UX), Data Sets, Billing, Production Systems, Problem Solving Skills, Persuasion Skills, Engineering, * 3-7 years of experience building and scaling end-to-end production systems, from data layer to UI

• Hands-on experience building with LLMs or agents, or the drive to get there fast
• Comfort working directly with customers (about 30% of the role)
• Strong problem-solving in fast-changing, ambiguous environments
• Clear, direct, persuasive communication
• Based in San Francisco or willing to relocate; in person 5 days a week, * Evals, observability or agent behavior-monitoring products
• Engineering pedigree from a strong product or infrastructure company
• Forward-deployed or solutions engineering experience
• Early-hire 0-to-1 startup experience or a founder background

Full benefits package, Equinox membership, a private chef, and direct influence on the product roadmap.

Company: Confidential - venture-backed technology companyLocation: San Francisco, CA (in person, 5 days per week)Compensation: $200,000 (about 3 years of experience) up to $300,000 (3-7 years); exceptional candidates case by caseEmployment Type: Full-timeVisa Sponsorship: Case by case for exceptional candidates, The client builds infrastructure for Agent Behavior Monitoring (ABM). Where traditional observability logs exceptions and latency, Judgment surfaces behavioral anomalies such as instruction drift and context-retrieval loss in production AI agents at scale, and hundreds of agent-building teams rely on it.

The company has raised $30M+ across its seed and Series A, led by Lightspeed with SV Angel, Valor Equity Partners, Nova Global and angels including Chris Manning, Michael Ovitz and Kevin Hartz.