STN Incorporated
STN Incorporated
STN Incorporated provides managed IT and cloud infrastructure for enterprises and teams building business-critical software, AI systems, and robotics. Its services include private CPU clouds, GPU One AI infrastructure, secure networking and storage, and ongoing cloud operations supported by 24/7 human support and high-uptime service-level agreements. The company also handles cybersecurity operations and incident response, compliance and risk management, backup and recovery, and technology procurement and lifecycle management. STN serves SaaS companies, AI builders and model developers, robotics firms, and regulated organizations including healthcare providers, with infrastructure designed to support audit readiness and frameworks such as SOC 2 Type II and HIPAA.

Principal AI Agent Systems Engineer, Horizon AI

Lead development of Horizon AI’s production fleet of autonomous agents for GPU infrastructure. Own agent evaluation, orchestration, autonomy service-level objectives, and safe operational actions.

Opis

  • Build evaluation tools for agent behavior, including real-incident scenarios, CI regression gates, and metrics for confidently incorrect outputs.
  • Define autonomy service-level objectives with the Chief Architect and provide evidence for advancing decisions from recommendations to actions.
  • Lead agent architecture across orchestration, tool dispatch, task decomposition, escalation, and read/write governance.
  • Improve agent reasoning explanations so teams can act on recommendations.
  • Turn operational runbooks into reasoning workflows agents can execute.

Zahteve

  • Have built and shipped production LLM agent systems, handling malformed tool outputs, loops, stalled states, and exhausted context.
  • Bring well-founded, specific views on how to evaluate agents.
  • Have experience with tool and function calling at scale.
  • Have experience with LLM tracing and online evaluation.
  • Have strong Python systems engineering fundamentals.
  • Have experience with multi-agent orchestration, handoffs, and context management.
  • Operational or SRE experience is a plus.
  • Human-in-the-loop system design experience is a plus.
  • Experience retrieving information from operational data is a plus.
  • Experience defining the actions an autonomous system may take is a plus.

Sorodna delovna mesta

CDW

AI Infrastructure Consulting Engineer, Compute and Storage

CDW

Design and validate GPU compute and high-performance storage solutions for enterprise AI and machine learning workloads. Help CDW customers implement infrastructure for AI training, fine-tuning, and inference.

Odpri