Senior Software Engineer (AI Inference & Runtime Platform)
New
A
AZXAI / Sustainability
Fully remote culture with a cluster of teammates in SeattleFull-TimeSenior
Salary$140K - $225K; $140K – $225K • Offers Equity • Offers Bonus
Apply NowOpens the employer's application page
Job Details
- Experience
- 5+ years
- Required Skills
- PythonKubernetesFastAPIRustTerraformDistributed Systems
Requirements
- 5+ years of experience shipping production systems in a systems language such as Rust, Go, C++, or Zig.
- Demonstrated experience operating complex Kubernetes workloads including controllers, operators, and autoscaling.
- Strong ability to threat-model isolation boundaries like namespaces, cgroups, seccomp, and hypervisors.
- Hands-on experience deploying or operating open-weight LLM serving infrastructure like vLLM or SGLang.
- Deep knowledge of distributed systems performance, measurement, and optimization.
- Practical experience with Rust (tokio), Python/FastAPI, Kubebuilder, KEDA, and GPU device plugins.
- Familiarity with isolation technologies such as Firecracker, Kata, or gVisor.
- Experience with secrets management, egress control, and stateful systems like pgvector, Qdrant, or Neo4j.
- Proficiency in multi-cloud infrastructure-as-code and observability tooling like OpenTelemetry.
- Bachelor's Degree or higher education.
- Ability to travel 2x per year for company summits.
Responsibilities
- Manage the serving tier for open-weight models including engine deployment, configuration, and cold-start strategy.
- Administer the Kubernetes layer for inference and sandbox workloads using operators, autoscaling, and GPU scheduling.
- Own the stateful data plane including vector and graph store deployment, scaling, and disaster recovery.
- Oversee the sandbox runtime and host-side control plane, including security threat modeling for isolation boundaries.
- Direct FastAPI control-plane services and infrastructure-as-code using Terraform/OpenTofu or Bicep.
- Build to open-source standards with reviewed PRs, documentation, and reproducible builds.
View Full Description & ApplyYou'll be redirected to the employer's site
