Applied AI Engineer

About the role

You will own the full lifecycle of AI agents that power frontline communication and automation for Zello's mission-critical users. You will translate ambiguous problems into production-ready agent workflows and ensure they deliver reliable value day after day. You will design evaluation frameworks that continuously measure agent quality and drive iterative improvements. You will act as the bridge between AI experimentation and operational excellence, turning prototypes into trusted tools. You will collaborate closely with product, operations, and engineering teams to scope, build, and refine AI capabilities. You will champion best practices in prompt engineering, context management, and tool use across the team. You will be accountable for the end state of deployed agents, owning their health, performance, and impact on real workflows.

Key facts

What you'll do

• Build AI agents and automations end-to-end, scoping use cases, defining interfaces, deploying solutions, and maintaining them in production.
• Write production Python that integrates LLM APIs, handling prompt construction, context management, token efficiency, and robust error handling.
• Integrate AI tools with Zello's existing systems such as Slack, Jira, HubSpot, and Snowflake through secure APIs, respecting rate limits and logging behavior.
• Create evaluation harnesses with automated quality scoring and regression detection to keep agent outputs consistent and trustworthy.
• Monitor deployed agents in production, tracking quality metrics, triaging failures, and prioritizing improvements based on real usage data.
• Manage human reinforcement workflows, reviewing agent outputs, curating feedback, and tuning agent behavior based on operational signals.
• Establish reusable components, patterns, and documentation that accelerate future agent development and raise the bar for the team.
• Communicate clearly with both technical and non-technical stakeholders, explaining what you built, why it matters, and where it needs attention.
• Independently scope and ship AI tools for new use cases, whether they come from stakeholder requests or your own initiative.
• Define and implement logging, observability, and alerting for AI workflows to ensure reliability and fast debugging.
• Partner with product to align agent behavior with business goals, ensuring outputs support frontline operations and safety requirements.
• Refine agent performance over time by analyzing interaction data, identifying edge cases, and updating prompts, tools, and fallbacks.
• Contribute to architectural decisions that balance innovation with maintainability, security, and scalability.
• Support on-call responsibilities for deployed agents, responding to issues and improving resilience based on live incidents.

Requirements

• You have 2-5 years of professional experience in software engineering, AI engineering, or a related technical role, having moved beyond entry-level fundamentals.
• You have written production Python and can point to real tools, integrations, automations, or shipped products you built.
• You understand LLM APIs practically, including prompt construction, context window management, token economics, and tool-use patterns.
• You decompose messy problems into clean components with well-defined interfaces and can explain your designs through abstractions and dependencies.
• You have integrated systems via APIs before, able to read API documentation, handle authentication, manage rate limits, and resolve real-world edge cases.
• You have a strong quality instinct, asking how you know something works and how you will know when it breaks, backed by tests and monitoring.
• You are comfortable with operational ownership, treating deployment as the beginning of responsibility for agent health in production.
• You pick up new frameworks, APIs, and domains quickly, adapting to changing requirements and technology landscapes.
• You are based in Austin, Texas, and able to work full-time onsite with the team.
• You are fluent in English for clear communication with cross-functional partners and stakeholders.
• You have a history of delivering reliable software that people can depend on in demanding environments.
• You understand the importance of security, privacy, and compliance when handling data in AI workflows.
• You are willing to work within standard working hours and respond promptly during incidents affecting deployed agents.
• You respect the operational nature of the role, including monitoring, human reinforcement, and continuous improvement.

Nice to have

• Experience building and deploying conversational or voice-first agent experiences.
• Familiarity with communication or collaboration platforms and their integration patterns.
• Knowledge of evaluation frameworks for language model outputs and agent behaviors.
• Background in high-availability systems where uptime and reliability are critical.
• Exposure to frontline or mission-critical applications where user impact is immediate.

Practical notes

This role is full-time and based in Austin, Texas. The position requires onsite presence during standard working hours and may involve on-call rotations for production support. Candidates must be eligible to work in the United States without sponsorship at this time. Travel is not required for this role. Visas are not currently sponsored. Only correspondence from the zello.com email domain is official; any requests for bank account information or checks should be treated as suspicious, and interested candidates should contact recruiting@zello.com with questions.