Senior Software Engineer (AI Inference & Runtime Platform)
AZX · Remote · Seattle ·
COMPENSATION
$140k – $230k
Listed on the employer's job board (Ashby)
- Senior level role
- Fully remote (US)
- Rust + Kubernetes
- AI Inference Platform
- No visa sponsorship
AZX accelerates positive impact in critical industries through AI transformation, specializing in physics-informed ML and enterprise solutions for climate challenges. You will own the layer where AI workloads physically execute, managing inference control planes and hardware-isolated sandboxing platforms.
The role involves building fork engines, guest agents, and model lifecycles using Rust, Kubernetes controllers, and FastAPI. You will ensure scale-to-zero economics, secure execution of untrusted code, and robust operational discipline across managed GPU clouds and customer clusters.
What you'll do
- Manage serving tier for open-weight models including deployment and cold-start strategies
- Administer Kubernetes layers for inference and sandbox workloads with autoscaling
- Own stateful data plane end-to-end with regularly tested restore procedures
- Oversee sandbox runtime lifecycle, execution, snapshotting, and isolation threat models
- Direct FastAPI control-plane services and infrastructure-as-code configurations
- Support backend services team by debugging issues and maintaining observability dashboards
- Maintain open-source posture with reviewed PRs, documentation, and reproducible builds
What you'll need
- 5+ years shipping production systems in a systems language like Rust, Go, C++, or Zig
- Experience operating Kubernetes workloads including controllers, scheduling, and node lifecycle
- Strong ability to threat-model isolation boundaries and apply security best practices
- Hands-on experience deploying open-weight LLM serving infrastructure like vLLM or SGLang
- Performance discipline in distributed systems with ability to measure and optimize latency
- Practical depth in Rust, Python/FastAPI, Kubernetes operators, and GPU device plugins
- Familiarity with isolation tech like Firecracker or gVisor and secrets management tools
- Comfort operating across AWS, Azure, GCP, and managed GPU clouds using Terraform
- Bachelor's Degree required, Master's is a plus
- Must be authorized to work in the United States full-time
Stack
- Rust
- Kubernetes
- Python
- FastAPI
- Terraform
- OpenTofu
- Bicep
- vLLM
- SGLang
- Firecracker
- Kata
- gVisor
- AWS
- Azure
- GCP
How you'll work
- Fully remote culture with team cluster in Seattle
- Must be able to travel twice a year for company summits
- Applicants must be authorized to work in the US
What you get
- Competitive early-stage startup compensation
- Bonus eligibility
- Health insurance with meaningful coverage for dependents
- Flexible paid time off
- Equity participation
Hiring process
- Written take-home assignment
- Live two-hour technical session with engineering team
- Apply to maximum of 2 roles at a time