Remote Live Verification Agent Jobs in Utah (NOW HIRING)

Bay Area (Hybrid) | Salt Lake City Area (Remote) | Full-Time Senior Engineer

Three person engineering teams are building what used to take thirty. Not by working harder, but by working differently. The engineers shipping at this pace don't write code. They write specs precise enough that agents implement them correctly. They build harnesses. CI gates, structural tests, linting rules, and architectural enforcement that mechanically prevent entire classes of agent mistakes. They design validation systems where agents write the tests and humans verify that features actually work from the user's perspective.

The code is a generated artifact. The spec, the harness, and the validation infrastructure are what engineers maintain.

This is how we work at Bolo.ai. We're hiring engineers who already work this way, or who have the depth to start.

Bolo AI is building the AI company for heavy industry.

These are the sectors the world depends on: energy, utilities, manufacturing, and industrial operations. They have been underserved by modern software and AI for too long. We are changing that with AI built for their messy, high-stakes operational reality.

Customers are already using Bolo to catch critical equipment failures, recover hidden cost impact, automate operational workflows, and put decades of industrial data to work.

Backed by True Ventures, Benchstrength, Accomplice, Analog Ventures, and Beat Ventures, we are a small, AI-native team working close to the customer to make their daily work faster, safer, and better.

You'll spend your time on four things:

• Specifications. You write behavioral specs, architectural constraints, and feature requirements that agents implement against. When agent output misses the mark, you tighten the spec. Not by adding more words, but by being more precise about what "correct" means. This requires understanding the system deeply enough to define its behavior at every layer.
• Harness. You build and maintain the infrastructure that keeps agents producing reliable code. Structural tests that enforce architectural boundaries. Linting rules where every failure message teaches the agent what went wrong. CI gates that reject drift. Structured knowledge bases agents can navigate. The principle: every class of agent mistake gets a mechanical fix so it never recurs.
• Validation. Agents write the code. Agents write the tests. You verify that features work from the user's perspective, under real deployment conditions, against edge cases that matter in production. You define scenarios and acceptance criteria. You build the end-to-end checks, behavioral verification, and automation that make this trustworthy at scale. When something breaks, your job is diagnosing whether the failure is in the spec, the harness, or the agent's implementation, and fixing the right layer.
• Architecture and operations. Our systems run across cloud providers and on-premises environments. You design modular abstractions, clean interfaces where deployment targets don't leak into application logic. You own production systems used by energy companies in regulated environments where failures have real consequences. Reliability, observability, and graceful degradation matter here.

7+ years of engineering experience, applied at a higher altitude. You need years of building and debugging production systems. Not because you'll write every line, but because you can't design a harness that catches real failures, write a spec that anticipates edge cases, or diagnose a broken feature across the full stack without that foundation. The depth serves the abstraction.

Systems thinking over code fluency. How components interact. Where failures cascade. What breaks when requirements change. What to anticipate before it happens. This is what agents are worst at and what matters most.

An agent-driven workflow. You already direct AI agents (Claude Code, Codex, Cursor, or similar) to handle implementation while you focus on architecture, specification, and validation. Or you have the engineering judgment to make that transition and the motivation to do it now.

Experience building the infrastructure around agents. CI enforcement, scenario-based testing, documentation systems agents can consume, structured knowledge bases - you've built some of this, or you have specific ideas about how and why.

Comfort making decisions with incomplete information. Startup. Requirements shift. The right approach isn't always obvious. You move forward, and you know when to ask versus when to make a call.

Direct communication. You give and receive honest feedback. You can disagree with a decision, say so clearly, and still commit to the outcome. We care about getting it right more than being right.

Enthusiasm for a field that reinvents itself quarterly. Tools change. Workflows get replaced. Best practices from three months ago become obsolete. You're energized by that. You see this as the most interesting period in the history of software.

Small, senior-leaning engineering team. Real ownership, direct impact, no layers between you and the work. We expect a lot from each other and give each other the room to deliver.

Sustainable pace over heroic sprints.

Bolo AI is headquartered in Palo Alto, backed by True Ventures, Benchstrength, Accomplice, J Ventures, and Beat Ventures.

• Competitive compensation with equity so you share in what we build together.
• Hybrid flexibility - in-person collaboration in Palo Alto with room to work how you're most productive.
• Early-stage ownership - join at a stage where your decisions shape the product, the architecture, and the engineering culture.
• Generous PTO and flexible working hours.

We evaluate how you work in an AI-native workflow. AI tool usage is expected, not just permitted. We're looking at engineering judgment. Can you write specs agents execute well against, build systems that catch real failures, and reason about problems across the full stack.

We'll be straightforward about our process, give you real information to evaluate us, and give you feedback regardless of outcome.

If this sounds like what you're already building toward, we'd like to talk.