AI Agent Infrastructure Lead

Sphere; San Francisco (CA); On-site; USD 230,000 - 260,000; Full time

Job summary

Sphere seeks an engineer to lead our internal AI agent enablement efforts in San Francisco, working to safely scale AI agents across engineering and operations. You’ll build Go/Python-backed systems that let agents accelerate workflows with robust safety and human review.

You’ll own the infrastructure, tooling, and workflows for agent deployment, iterate on sandbox environments, and help establish patterns for context, permissions, and observability across Sphere’s platforms.

Qualifications

• Experience building production-quality software.
• Experience in AI agents, coding agents, or AI agent enablement.
• Comfort with backend systems, infrastructure, and CI tools.
• Strong judgment on autonomy, safety, and human review.

Responsibilities

• Ship AI agent features to improve engineering velocity.
• Iterate on agent sandbox environments and code inspection workflows.
• Lead internal efforts to enable autonomous AI agents across teams.
• Own infrastructure, tooling, and workflows for safe agent use.

Skills

AI agents

Developer tooling

Backend systems

CI/CD

Safety & permissions

Job description

About Sphere

Every breakthrough in trade infrastructure has followed the same pattern: reduce a transaction cost, expand the market. Containerization for goods. SWIFT for money. Stripe for payments. Compliance is one of the last and largest — and the hardest, because trade rules aren't data to be looked up. They're a complex adaptive system with 190+ sovereign jurisdictions, in different languages, changing constantly, reacting to each other.

Sphere built the system that solves it. Our AI (TRAM) ingests global trade law, interprets it, resolves conflicts across jurisdictions, and produces compliance determinations more reliable than human experts. We handle the entire lifecycle—calculation, registration, filing, remittance—at millisecond latency with zero downtime.

• Backed by a16z and YC. $21M Series A, 30%+ month-over-month growth, customers include ElevenLabs, Replit, Deel, Runway, and Lovable.
• Small team, global surface area. Everyone owns a domain that would be a full team at a larger company. San Francisco, five days in office.
• The problem keeps compounding. Expanding into input tax, withholding, e-invoicing, tariffs—each multiplies the complexity. Tens of millions of transactions today, billions ahead.

The Role

Sphere is looking for an engineer to lead our internal AI agent enablement efforts. You’ll build the systems that let AI agents safely and effectively increase velocity across. Sphere, starting with engineering and expanding into ops, customer success, tax research, and implementation workflows.

What You’ll Do

Within Days

• Ship AI agent features that help Sphere’s engineering team use agents more effectively and responsibly.
• Iterate on versions of Sphere’s agent sandbox environments.
• Create workflows where agents can inspect the codebase, run local infrastructure, make changes, run tests, and prepare work for human review.
• Work directly with engineers to identify high-leverage internal workflows where agents can create immediate velocity.

Within Months

• Lead Sphere’s internal efforts to enable AI agents to act more autonomously across engineering, ops, customer success, tax research, and implementation.
• Build “Goose” for Sphere: the internal AI agent layer that helps agents understand and operate across Sphere’s systems.
• Own the infrastructure, tooling, and workflows that let agents safely take on more complex internal work over time.
• Establish the patterns for how Sphere uses agents internally, including context, permissions, review, observability, and escalation.

Requirements

• Experience building production-quality software.
• Experience in AI agents, coding agents, internal developer tooling, or AI agent enablement.
• Comfort working across backend systems, infrastructure, local development environments, CI, and internal tools.
• Strong judgment around autonomy, safety, permissions, and human review.
• High agency. You can take a vague internal problem and turn it into a working system people actually use.
• Strong attention to detail. Agents are only useful here if they improve speed without reducing correctness.

Who You Are

• You’re a Dog. You've been underestimated, gone through struggle, and never stopped running. You have a chip on your shoulder and enormous drive. You look at Stripe, Deel, and Flexport all punting on compliance and think: good, that means the opportunity is ours. Hunger beats pedigree.
• Early stage is in your bones. You've built things where there's no playbook and nobody handing you the answer. You define the problem instead of waiting for instructions.
• You own it end to end. Give you a goal and you figure out your own path. Small team, global surface area—everyone owns a domain that would be a full team at a larger company. No one tells you how.
• You believe speed and accuracy are both possible. We're building a complex product that requires robustness and 100% uptime, and we have to build at our customers' pace. Move fast. Don't break things. Both.

This Won’t Be a Fit If

• You need structure handed to you or ambiguity feels draining rather than motivating.
• You want to manage people more than own hard problems (we're a flat, experienced team — everyone builds).
• You’re used to "good enough" shipping (small errors have outsized impact here).

Compensation Range: $230K - $260K