Staff AI Engineer - USA

podium81; United States; Remote; USD 180,000 - 240,000; Full time

Benefits offered by this job

Medical/dental/vision

Life and disability insurance

Parental leave

Fertility benefits

Retirement matching

Four-day summer weekends

Job summary

podium81 is seeking a senior software engineer to design and scale a production AI agent platform handling customer conversations across voice, text, and chat. You will work on distributed services, APIs, infrastructure, and reliability to deliver accurate, responsive experiences for businesses and their customers.

You will own features end-to-end, prototype rapidly with real interaction data, and collaborate with AI/ML, product, and engineering teams.

Qualifications

• 10+ years in professional software engineering.
• At least 1 year deploying production AI agents.
• Experience with distributed/high-throughput systems.
• Clear communication and cross-team collaboration.
• Willingness to work across infra, APIs, and user-facing software.

Responsibilities

• Build high-volume, low-latency services for conversational workflows.
• Design APIs and infrastructure for multi-turn interactions across channels.
• Own features through architecture, implementation, deployment, and operations.
• Prototype quickly and use real interaction data to improve performance.
• Establish monitoring and operational practices, tracking accuracy and latency.
• Collaborate with engineering, product, and AI/ML teams to deliver end-to-end capabilities.

Skills

Go

Python

Elixir

Distributed systems

Low-latency

APIs

Communication

Tools

LangGraph

CrewAI

AutoGen

Job description

Role overview

Design and scale a production AI agent platform that handles customer conversations across voice, text messaging, and chat. The work spans distributed services, APIs, infrastructure, and operational reliability, with a focus on making real-time interactions accurate, responsive, and useful to businesses and their customers.

Responsibilities

• Build high-volume, low-latency services for conversational workflows.
• Design APIs and infrastructure for multi-turn interactions across channels.
• Own features through architecture, implementation, deployment, and ongoing operations.
• Prototype quickly and use real interaction data to improve system performance and user experience.
• Establish monitoring and operational practices, tracking agent accuracy and latency.
• Partner with engineering, product, and AI/ML colleagues to deliver end-to-end capabilities.

Requirements

• At least ten years of professional software engineering experience using a modern language such as Go, Python, or Elixir.
• At least one year deploying and maintaining production AI agents that use tools, APIs, or real-world workflows.
• Demonstrated success designing and operating distributed or high-throughput systems.
• Strong problem-solving skills and comfort working through ambiguity in large systems.
• Clear communication and ability to collaborate across teams.
• Willingness to work across infrastructure, APIs, and user-facing software as needed.
• Ability to adapt in a fast-paced environment with changing priorities.

Nice to have

• Two or more years operating production AI agents.
• Experience evaluating language model behavior for accuracy, safety, reliability, and cost.
• Knowledge of prompt design, context engineering, and guardrails for dependable agent behavior.
• Experience with agent frameworks such as LangGraph, CrewAI, or AutoGen, including orchestration, memory, and multi-step workflows.
• Hands-on fine-tuning or data curation experience.

Benefits

• Benefits include medical, dental, and vision coverage; life and disability insurance; paid parental leave; fertility benefits; retirement matching; and generous vacation, including three four-day summer weekends.