Staff Software Engineer, AI

We are looking for a Staff Software Engineer, AI to help build the core platform that powers enterprise-grade intelligent agents in Minneapolis, Minnesota. In this role, you will tackle complex technical challenges across distributed systems, applied artificial intelligence, security, and platform engineering while creating reliable capabilities for demanding business use cases. You will work closely with product, engineering, machine learning, and security teams to guide architectural decisions and deliver scalable agent-driven solutions.

Responsibilities:

• Drive the technical direction of the agent platform, shaping how agents plan tasks, make decisions, manage execution flow, and produce structured outcomes in production environments.
• Develop multi-layered memory capabilities that support short-term context, historical interactions, knowledge retrieval, and persistent workflow state while enforcing retention and access policies.
• Build secure execution frameworks for agent operations using isolated containerized environments with strong controls for resources, network access, credentials, and tenant separation.
• Create dependable orchestration patterns that enable asynchronous processing, delegated work, checkpointing, restartability, retry logic, and recovery from operational failures.
• Implement extensible integrations with internal and external tools, ensuring strong authentication, authorization boundaries, and protections against unsafe or manipulated actions.
• Establish evaluation frameworks and observability practices to assess quality, reliability, latency, correctness, and cost, then use findings to improve agent performance over time.
• Partner with cross-functional stakeholders to translate high-impact business workflows into scalable AI agent capabilities that support complex enterprise needs.
• Strong experience building backend or platform systems using Python and at least one additional language such as TypeScript, Kotlin, Rust, or Java.
• Deep understanding of artificial intelligence and machine learning concepts, including hands-on work with agent-based AI systems or related intelligent automation solutions.
• Background designing cloud-native applications using technologies such as Docker and Kubernetes in secure, scalable production environments.
• Proven ability to architect APIs, distributed services, and resilient backend systems that support high availability and operational reliability.
• Experience implementing security-focused engineering practices, including isolation strategies, credential protection, least-privilege access, and policy enforcement.
• Familiarity with evaluation, testing, tracing, and monitoring approaches used to measure and improve AI system performance.
• Ability to collaborate effectively across engineering, product, machine learning, and security teams on technically complex initiatives.