Principal Engineer, Autonomous Agent Fleet & MAS

STN, Inc.; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

STN, Inc. is building an AI-first platform where a fleet of autonomous agents diagnoses GPU infrastructure, reasons about what to do, and acts under controlled risk.

This Principal to Distinguished role focuses on proving agent decisions with evidence, shaping the governance for actions, and expanding safe autonomy in production. You will design evaluation harnesses, define performance SLAs, and own the architecture and explainability of agent-driven operations.

Qualifications

• Built and shipped LLM-based agentic systems in production.
• Strong opinions about evaluation.
• Experience with tool and function calling at scale.
• Strong Python systems engineering fundamentals.
• Experience with multi-agent orchestration and context management.

Responsibilities

• Build the evaluation harness for agent behaviour: scenario suites drawn from real incidents, regression gating in CI, and metrics that catch an agent being confidently wrong.
• Define the autonomy SLO with the Chief Architect, and own the evidence presented when we propose moving a decision from recommendation to action.
• Own the agent architecture: orchestration, tool dispatch, task decomposition, escalation, and the governance boundaries that separate read from write.
• Improve how agents explain their reasoning, because an unexplained recommendation does not get acted on.
• Continue encoding operational runbooks into agent-executable reasoning.

Skills

LLM Agents

Tool Calling

Python

Multi-agent Orchestration

Context Management

LLM Tracing

Evaluation Focus

Handoff

Job description

STN, Inc. is building an AI-first platform where a fleet of autonomous agents diagnoses GPU infrastructure, reasons about what to do, and acts under controlled risk.

This Principal to Distinguished role focuses on proving agent decisions with evidence, shaping the governance for actions, and expanding safe autonomy in production. You will design evaluation harnesses, define performance SLAs, and own the architecture and explainability of agent-driven operations.