Staff AI Engineer - Utah

We are looking for a talented Staff AI Engineer to help build and scale our AI Agent platform—a powerful system that autonomously interacts with customers, handling millions of conversations every month. In this role, you’ll design and deliver the software that enables local businesses to manage complex customer interactions automatically, book more appointments, and serve their customers more effectively across multiple channels (e.g., voice, SMS, chat).

If you thrive in fast-paced, highly iterative environments, enjoy solving complex distributed systems challenges, and want to see your work drive immediate business impact, this role is for you!

• →Build and scale the AI Agent platform — enabling high-volume, real-time conversational workflows that deliver accuracy and low latency at scale.
• →Design and implement APIs, services, and infrastructure that power multi-turn, cross-channel customer interactions.
• →Own the full lifecycle: architecture, implementation, deployment, and ongoing reliability.
• →Prototype rapidly, iterate with live interaction data, and continuously improve system performance and user experience.
• →Implement observability, monitoring, and operational best practices to ensure reliability in production, focusing on agent accuracy and latency.
• →Collaborate with engineers, product managers, and AI/ML scientists to deliver end-to-end features that power critical business outcomes.

• 10+ years of professional software engineering experience with at least one modern language such as Go, Python, or Elixir.
• 1+ years of professional experience deploying and maintaining AI agents in production environments that interact with tools, APIs, or real-world workflows.
• Proven success designing and maintaining distributed or high-throughput systems.
• Strong problem-solving ability and comfort navigating ambiguity in large-scale systems.
• Excellent communication skills and the ability to work effectively across teams.
• A willingness to work across the entire stack—from infrastructure to APIs to user-facing components—wherever the problem needs solving.
• Ability to thrive in a fast-paced environment with shifting priorities.
• Must be willing to work on site, 5 days per week.

• 2+ years of professional experience deploying and maintaining AI agents in production environments that interact with tools, APIs, or real-world workflows.
• Practical experience designing and implementing evaluations for LLM behavior — including accuracy, safety, reliability, and cost monitoring.
• Strong understanding of prompt design, context engineering, and guardrail strategies for dependable, interpretable agent behavior.
• Experience with modern agent frameworks such as LangGraph, CrewAI, or AutoGen, including multi-step reasoning, memory, and orchestration patterns.
• Hands-on experience with fine-tuning and data curation for improving model performance.

• Podium is the best place to work to:
  • Join the leaders in AI agents
  • Unlock career-defining growth
  • Build with world-class talent
  • Make a real impact on local business