Software Engineer — AI-Native Full Stack

Bolo AI•Salt Lake City, UT

3h•Hybrid

About The Position

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 builds generative AI systems for the energy industry, making daily work faster, safer, and better for heavy industry workers. We have Fortune 500 contracts, production deployments, and growing enterprise demand. We're scaling. Energy adds real constraints. Regulatory compliance, data residency, operational technology integration, deployment across cloud and on-premises infrastructure. These constraints make the architecture harder and the work more interesting. 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.

Requirements

7+ years of engineering experience, applied at a higher altitude.
Experience building and debugging production systems.
Systems thinking over code fluency.
An agent-driven workflow, directing AI agents for implementation while focusing on architecture, specification, and validation.
Experience building the infrastructure around agents (CI enforcement, scenario-based testing, documentation systems, structured knowledge bases).
Comfort making decisions with incomplete information.
Direct communication skills: ability to give and receive honest feedback and commit to outcomes.
Enthusiasm for a rapidly evolving field.

Responsibilities

Write behavioral specs, architectural constraints, and feature requirements that agents implement against.
Build and maintain the infrastructure that keeps agents producing reliable code, including structural tests, linting rules, CI gates, and structured knowledge bases.
Verify that features work from the user's perspective, under real deployment conditions, against edge cases that matter in production.
Design modular abstractions and clean interfaces for systems running across cloud providers and on-premises environments.
Own production systems used by energy companies in regulated environments.