Full-Stack Engineer

Ersilia; San Francisco (CA); On-site; USD 200,000 - 400,000; Full time

Job summary

Ersilia, based in San Francisco, is seeking a Full-Stack Engineer to own the product experiences and agent infrastructure that make the agent improvement loop legible and actionable for engineering teams.

You will talk to customers, define what to build, implement it, and iterate until the product delivers value across data layer to UI, including agent swarm interfaces, verification platforms, and the SDK.

Qualifications

• Experience building and scaling end-to-end production systems, from data layer to UI.
• Hands-on experience building with LLMs or agents, or demonstrable drive to get there fast.
• Comfort working directly with customers to understand needs and solve real-world problems.

Responsibilities

• Shape how our Agent runs large-scale parallel investigations across thousands of production traces, merging failure modes and drift signals into a single actionable answer.
• Build the platform for verifying agent changes: hosted simulated environments for stateful agent evals and trajectory replay.
• Design how engineers understand long traces, tool calls, decisions, and failures—making complex reasoning trajectories legible.
• Build the swarm UX so engineers can monitor parallel investigations and steer investigations in the right direction.
• Own the improvement loop: workflows turning production trajectories into datasets, judges, and regression checks.
• Own platform infrastructure: workspaces, roles, permissions, billing, usage, and limits for teams running many agents.

Skills

End-to-end systems

LLMs/agents

Customer-facing

Problem-solving

Communication

In-person in SF

Job description

About The Company

We build infrastructure for Agent Behavior Monitoring (ABM). While traditional observability focuses

on logging exceptions and latency, ABM surfaces behavioral anomalies such as instruction drifts and context

retrieval loss in scaled production environments. Hundreds of teams building autonomous agents rely on our platform to understand how their systems are behaving post-deployment. The team has raised $30M+ across two rounds in the past five months.

About the Role

We’re hiring a Full-Stack Engineer to own the product experiences and agent infrastructure that

make the agent improvement loop legible and actionable for engineering teams. This is not a role where you

implement specs handed down: you will talk to customers, define what to build, build it, and iterate until it is

great. The role spans from the data layer to the UI, including the agent swarm interfaces, verification platforms,

and the SDK layer that lets developers summon our mid-development. About 30% of the role is customer-facing.

What You’ll Own

1. Shape how our Agent runs large-scale parallel investigations across thousands of production traces, merging failure modes, tool errors, regressions, and drift signals into a single actionable answer

1. Build the platform for verifying agent changes: hosted simulated environments for stateful agent evals, trajectory replay against changed agents, and monitors for unintended behavior

1. Design how engineers understand long traces, tool calls, decisions, and failures: making a thousand-step reasoning trajectory legible in minutes

1. Build the swarm UX so engineers can watch parallel investigations, redirect investigators that go down the wrong path, and consume findings without reading hundreds of reports

1. Own the improvement loop: the workflows that turn production trajectories into datasets, judges, and regression checks so the path from found problem to verified fix feels like one motion

1. Build and maintain the SDK and terminal-first experience so agent development sessions can summon our agent as a subagent mid-development

1. Own platform infrastructure: workspaces, roles, permissions, billing, usage, and limits for teams running many agents across many environments

Requirements

Must-Have

1. Experience building and scaling end-to-end production systems, from data layer to UI

1. Hands-on experience building with LLMs or agents, or demonstrable drive to get there fast

1. Comfort working directly with customers to understand their needs and solve real-world problems

(approximately 30% of the role is customer-facing)

1. Strong technical problem-solving ability in fast-changing, ambiguous environments

1. Excellent communication skills: clear, direct, and persuasive across technical and non-technical audiences

1. Based in San Francisco or willing to relocate; 5 days per week in-person

Nice-to-Have

1. Prior evals, observability, or agent behavior-monitoring product experience

1. Strong engineering pedigree from a solid product company (e.g. Roblox, Snapchat, Tesla); top-tier infra background (e.g. Databricks) is a bonus

1. Prior forward-deployed or solutions engineering experience

1. Prior 0-to-1 startup experience as an early hire

1. Founder background or strong founder-to-be signal

1. Comfort across the full stack with backend and infrastructure weight

Visa Sponsorship: H-1B, O-1, OPT

NB: We work in person in San Francisco. We're open to sponsoring truly exceptional candidates on a case-by-case basis, but our main scope will be candidates who don't require this.

Compensation

Junior level (3 years experience): $200K

Mid to senior level (3-7 years experience): up to $300K

Exception: exceptional AI-savvy FDE leads can reach $400K on a case-by-case basis