Software Engineer

About the role

About Varick

Varick builds AI agents that take over real operational workflows inside the world's largest

enterprises. Our forward-deployed engineers and strategists embed with client teams, map how

work actually runs, then our engineers build the agents into production. We're venture-backed,

revenue-generating from day one, and already in production inside several of these companies.

Every deployment compounds the platform, our Varick OS, which is where all agents are spun up,

monitored, optimized, and deployed. We're building the first enterprise-ready agent-building

platform, informed by the depth of information we uncover first-hand while embedded with our

clients. You'll be joining an elite team from Meta, AWS Bedrock, Citadel Securities, McKinsey, BCG,

Stanford, and more.

The role

You'll build Varick OS and the agents that run on it. That covers the runtime that executes

long-running workflows against enterprise ERP and CRM environments, the retrieval and context

layer those agents reason over, the eval and trace infrastructure that keeps quality measurable, the

model layer that keeps us provider-agnostic, and the deployment tooling that ships all of it into

environments we don't control.

The surface area is large. Decisions you make in your first quarter will still be load-bearing in two

years. You'll work alongside our lead engineer, who built the current stack from scratch.

This is not a client-facing role. Our forward-deployed team runs the audits and the client interviews,

then hands you the workflow spec. You build it, and pull whatever repeats back into the platform so

the next client is faster.

How We Build

We run an agent-driven development workflow: thorough specs up front, PRs graded against those

specs, and eval suites that gate what ships. It's how a small team holds velocity without the quality

drift that usually comes with it. You'll work inside this process and help sharpen it, including

judgment calls on where more rigor is warranted as we manage releases across multiple client

deployments.

What You'll Do

Build the agent runtime. Long-running workflows against enterprise systems that go down mid-run. Durable execution, safe retries, idempotency, retrieval and context assembly, and human approval gates that hold up when a step touches a client's general ledger.

Own the model layer. Provider-agnostic routing with real fallback, cost and latency budgets, and no lock-in to any single vendor.

Build evals and tracing. Golden sets, regression suites, and traces over every intermediate step, so we catch a drop in agent quality before a client emails us about one.

Ship into client environments. Package, deploy, version, and upgrade the platform across single-tenant deployments, including into a client's own cloud account.

Turn audits into production agents. Take workflow specs from our forward-deployed team, interrogate them, build them, and generalize the parts that repeat.

What we're looking for

3+ years building production software, with real ownership of systems other people depended on.

Strong backend and distributed systems fundamentals: state, concurrency, idempotency, failure handling, and the instinct to ask what happens when a dependency disappears mid-request.

Experience operating production systems at scale: Kubernetes, cloud infrastructure, and release management across multiple deployments and versions.

At least one LLM system shipped to real users, and a clear account of how it failed in production. We care more about the failure story than the launch.

A working understanding of inference economics, evaluation, and model behavior. You should know what a token costs at scale, and why an agent that works in a demo fails on the tenth run.

Fluency with AI-native development tools, and a view on where they earn their keep and where they produce confident garbage.

A habit of interrogating a spec instead of implementing it obediently. The five questions you ask before writing code are worth more here than how fast you write it.

Comfort with fast, low-process development, paired with the judgment to know when more rigor is warranted.

A track record of digging into code, data, and root causes directly rather than escalating.

Strong, proactive communication with both engineers and non-technical stakeholders. Your specs come from strategists, and the gaps in them are yours to surface early.

Nice to have

Experience shipping software into environments you don't control: BYOC, self-hosted, on-prem, or air-gapped.

Durable execution or workflow orchestration experience (Temporal or similar)

Enterprise environments with strict security and reliability requirements (SOC 2, on-call, incident response)

Deep familiarity with an enterprise ERP or CRM system of record: SAP, Oracle, NetSuite, Salesforce, Workday.

Founding or early engineer experience at a startup.

What we offer

Meaningful equity at a stage where it still compounds, architecture decisions that are yours to make, flexible PTO, lunch and dinner in the office, Ubers home when you stay late, and monthly team dinners.

Logistics

On-site in our San Francisco Financial District office, 5–6 days a week. Startup hours, for startup upside.

Equal Opportunity

We are an equal opportunity employer. All qualified applicants will receive consideration without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, or protected veteran status.