Applied AI Engineer

IMPORTANT: Please be aware, scammers may try to impersonate Zello by reaching out regarding job opportunities. We will never ask you for bank account information, checks, or other sensitive information as part of our hiring process. All correspondence will come from the zello.com email domain. If you’re unsure, please email recruiting@zello.com with questions.

ABOUT ZELLO

Zello is a voice-first communication platform, powered by our industry-leading push-to-talk technology, to improve collaboration and productivity for desk-less workers. With over 175+ million users, we’re the #1 rated push-to-talk app in the world, delivering 9 billion (yes, with a B) messages a month.

At Zello, our company values are at the heart of what we do everyday. We’re proud to serve the frontline, we’re privileged to connect people in times of crisis across the globe, and we’re honored to support first responders.

And this is where you come in.

The AI & Data team has more high-value AI use cases than capacity to build them. Today, the team leads agent development directly alongside many other responsibilities, and this work needs a dedicated builder. This hire will be one of the first few Applied AI Engineers at Zello, responsible for taking AI agents from prototype to production and then owning their ongoing health: monitoring quality, managing human reinforcement workflows, and driving continuous improvement.

AFTER A SUCCESSFUL FIRST YEAR, YOU WILL

• Shipped at least 3 production-grade AI agents within your first 90 days that internal teams actively use (Slack-integrated agents, workflow automations, data-driven assistants)
• Built evaluation harnesses for deployed agents with automated quality scoring and regression detection
• Integrated AI tools with Zello's existing systems (Slack, Jira, HubSpot, Snowflake) via APIs, with proper logging and monitoring in place
• Established reusable code patterns and component libraries that make future agent development faster
• Taken ownership of deployed agent operations: monitoring performance, overseeing human reinforcement workflows, triaging failures, and driving measurable improvement in agent quality over time
• Independently scoped and shipped AI tools for new use cases, whether identified by stakeholders or discovered on your own

WHAT YOU'LL DO

• Build AI agents and automations end-to-end: from scoping the use case through deployment and ongoing maintenance
• Write production Python code that integrates LLM APIs (prompt construction, response handling, context management, tool use) into real workflows
• Connect AI tools with Zello's systems (Slack, Jira, HubSpot, Snowflake) through APIs, handling authentication, rate limits, error cases, and logging
• Monitor deployed agents in production: track quality metrics, triage failures, and ship improvements based on real usage data
• Manage human reinforcement operations: review agent outputs, maintain feedback loops, and tune agent behavior based on reinforcement signals
• Build and maintain evaluation harnesses that catch regressions and measure agent quality programmatically
• Create reusable components, patterns, and documentation that raise the bar for future development on the team
• Communicate clearly with technical and non-technical stakeholders about what you've built, what's working, and where things need attention

WHO YOU ARE

• You have 2-5 years of professional experience in software engineering, AI engineering, or a related technical role. You're past the point of needing to learn basic professional work habits, but you haven't calcified into a single way of doing things.
• You've written production Python and can point to real things you've built with it: tools, integrations, automations, shipped products. Not just notebooks or coursework.
• You understand LLM APIs at a practical level. You can construct prompts, manage context windows, reason about token economics, and work with tool-use patterns.
• You decompose messy problems into clean components with well-defined interfaces. When you describe a system you've built, people can follow the logic because you think in terms of abstractions, dependencies, and failure modes.
• You've integrated systems via APIs before. You can read API docs, handle auth, manage rate limits, and deal with the inevitable edge cases of real-world integrations without getting stuck.
• You have a quality instinct. You naturally ask "how do I know this is working?" and "how will I know when it breaks?" You write tests and build monitoring because you care about what happens after you ship, not because someone told you to.
• You're comfortable with operational ownership. You don't treat deployment as the finish line. You monitor what you build, notice when things drift, review agent outputs, and do the sometimes unglamorous work of keeping AI systems healthy in production.
• You pick up new frameworks, APIs, and domains qu