Senior AI Systems Engineer - End-to-End LLM Ops | Equity

Zello; Austin, Northern (TX, KY); Hybrid; USD 140,000 - 190,000; Full time

Job summary

Zello is seeking an experienced software engineer to join the AI & Data team, building agent systems that power frontline workers.

You will design eval suites, ship end-to-end ML-enabled features, review PRs, monitor production, and coach teammates to raise engineering standards. This IC role emphasizes impact over titles, with focus on robust, testable systems and practical solutions. You'll collaborate across product and platform teams, triage failures, and ensure code quality and reliability.

Qualifications

• You learned to program properly and can reason about code you did not write.
• You build things nobody asked you to build.
• You treat tests and evals as part of shipping, not cleanup afterward.
• You give code review feedback people act on and coach rather than direct.
• You connect engineering standards to outcomes rather than to taste.
• You hold a high bar without making people feel small.
• You have operated production systems that others depended on.

Responsibilities

• Build LLM-backed systems end to end and put them in front of people who are not engineers.
• Design eval suites and monitoring before shipping, not after something breaks.
• Review agent pull requests and explain why a design will or will not hold up.
• Operate what you ship: triage drift, chase down silent failures, fix root causes.
• Set engineering conventions the team actually adopts - testing, structure, error handling.
• Pair with and coach teammates who are strong analysts and newer to software craft.
• Tell us when AI is the wrong tool for a problem, before we build it.

Job description

Zello is seeking an experienced software engineer to join the AI & Data team, building agent systems that power frontline workers.

You will design eval suites, ship end-to-end ML-enabled features, review PRs, monitor production, and coach teammates to raise engineering standards. This IC role emphasizes impact over titles, with focus on robust, testable systems and practical solutions. You'll collaborate across product and platform teams, triage failures, and ensure code quality and reliability.