Level: Staff (MTS 4) · Reports to: Chief AI Officer, later the Senior Engineering Manager
The role. Build agents and the tools they use. Hands-on work on the reasoning layer, alongside the Agent Fleet Lead, with regular embeds beside the operators whose decisions you are encoding.
You will
Extend and maintain the tool surface across our infrastructure and business systems, which needs ongoing development and consolidation
Implement agents that diagnose fleet conditions and produce recommended actions with visible reasoning
Translate operator runbooks and tacit knowledge into agent behaviour, largely by sitting with the operators
Build evaluation fixtures from real historical incidents and measure agent performance against them
Rotate through Systems and SRE embeds
You have
Shipped production software with LLMs in the loop, including the unglamorous parts: retries, timeouts, malformed output, token and cost control
Strong Python
Experience building tool or function-calling interfaces that give models structured access to external systems
A demonstrable recent record of building and shipping rather than designing and reviewing
Curiosity about infrastructure and willingness to learn it from the people who run it
Nice to have: async Python at scale, retrieval pipelines, OpenTelemetry, prior work on evaluation harnesses
Skills Required
- 6+ years of experience in platform engineering, SRE, or cloud engineering at scale
- Deep Kubernetes expertise, including CRDs, operators, and multi-tenant patterns
- Strong programming skills in Go, Python, or both
- Experience operating GPU clusters or AI infrastructure at production scale
- Bachelor's degree in computer science or equivalent experience
- Experience with NVIDIA GPU Operator, MIG, MPS, and NCCL operator patterns
- Familiarity with Slurm operator, Run:ai, KubeRay, or comparable AI orchestration
- Service mesh experience with Istio, Linkerd, or similar and multi-cluster networking
- Open source contributions in the cloud-native or AI infrastructure ecosystem
What We Do
STN, Inc. is a managed technology and infrastructure provider serving enterprise, regulated, and AI-driven organizations. It designs, operates, and supports secure, scalable systems, including managed IT, cloud and platform services, cybersecurity, data management, compliance engineering, enterprise hardware and software, and GPU One, its GPU-as-a-Service platform for AI training, tuning, inference, and other high-performance workloads. STN emphasizes reliability, audit readiness, and ongoing human support.
