Careers.Azx.Io
Senior Software Engineer (AI Inference & Runtime Platform)
Seattle, Remote. Posted 2 months ago
The role
You will own the inference control plane and the agent-sandboxing platform. This involves managing open-weight model serving, Kubernetes workloads, and hardware-isolated microVMs.
What you will do
- Manage the serving tier for open-weight models
- Administer the Kubernetes layer for inference and sandbox workloads
- Own the stateful data plane end to end
- Oversee the sandbox runtime and its host-side control plane
- Direct the FastAPI control-plane services, Terraform/OpenTofu, Bicep, and the dashboards
- Run the layer the backend services team builds on
- Manage the open-source posture
Required qualifications
- 5+ years of shipping production systems in a systems language
- Rust, Go, C/C++, or Zig
- Operated Kubernetes workloads including controllers, operators, scheduling, autoscaling, or node lifecycle
- Ability to threat-model isolation boundaries
- Hands-on experience deploying or operating open-weight LLM serving infrastructure
- Practical depth in Rust (tokio), Python/FastAPI, Kubernetes operators, KEDA, Karpenter, or GPU device plugins/DRA
- Familiarity with isolation technology (Firecracker, Kata, gVisor, or comparable)
- Familiarity with secrets management and egress control (Vault/KMS-class)
- Familiarity with hosting stateful systems (vector stores like pgvector/Qdrant, graph stores like Neo4j)
- Comfort operating across cloud and GPU substrates (AWS/Azure/GCP) using infrastructure-as-code and observability tooling
- Bachelor's Degree
Nice to have
- Master's is a plus
Benefits
- Competitive early-stage startup compensation
- Bonus eligibility
- Health insurance with meaningful coverage for dependents
- Flexible paid time off
- Equity
Before you apply
- Must be able to travel 2x/year for company summits
- Applicants must be currently authorized to work in the United States on a full-time basis
- We are unable to sponsor or take over sponsorship of employment visas at this time
- Interview process includes a written take-home assignment followed by a live two-hour technical session
- Please only apply to a maximum of 2 roles at a time
About the company
AZX specializes in physics-informed ML and enterprise AI solutions that address climate and sustainability challenges. They work on challenges in clean energy, decarbonization, climate risk, energy systems, and global economics.