Cloud Software Infrastructure Engineer

  • Prime Team Partners
  • Seattle, Washington
  • Full Time

AI Inference Infrastructure Software Engineer (Kubernetes / Cloud)

Seattle, WA (Hybrid - 3 days/week onsite)

Compensation: Targeting $170-210k, meaningful start up equity

A fastmoving AI engineering team is looking for an Inference Infrastructure Software Engineer to build and operate the Kubernetes and cloud backbone behind largescale accelerated inference workloads. If you thrive at the intersection of distributed systems, cloud infrastructure, and highperformance AI, this role puts you right at the core of nextgeneration inference platforms. If you want to help push AI inference to its performance limits and build the infrastructure that makes it possible, we'd love to connect.

What You'll Do

  • Build and operate Kubernetes infrastructure powering largescale inference services
  • Run accelerated workloads with strict latency, throughput, and reliability requirements
  • Manage AWS, GCP, and onprem environments across networking, storage, IAM, and observability
  • Develop automation and tooling in Python, Bash, and Go to streamline deployments and scaling
  • Partner with ML, runtime, and hardware teams to productionize new inference capabilities
  • Contribute to capacity planning, cost optimization, and reliability engineering
  • Participate in oncall rotation for critical services

What You Bring

  • 3-5 years of handson Kubernetes experience (EKS, GKE, or selfhosted)
  • 2-3 years operating production workloads on AWS or GCP
  • Experience running ML or accelerated inference services at scale
  • Strong skills in Python, Bash, and Go
  • Deep understanding of GPU/accelerator scheduling, device plugins, and cluster performance
  • Experience with IaC (Terraform/Pulumi), config management (Ansible/Puppet/Salt), and GitOps (Argo/Flux)
  • Comfortable operating in fastmoving, earlystage environments

Bonus Points

  • Experience with inference servers (Triton, vLLM, TGI)
  • Exposure to nonGPU accelerators (FPGAs, ASICs)
  • Background in SRE, observability, or performance engineering
  • Experience building customerfacing API platforms

Prime Team Partners is an equal opportunity employer. Prime Team Partners does not discriminate on the basis of race, color, religion, national origin, pregnancy status, gender, age, marital status, disability, medical condition, sexual orientation, or any other characteristics protected by applicable state or federal civil rights laws. For contract positions, hired candidates will be employed by Prime Team for the duration of the contract period and be eligible for our company benefits. Benefits include medical, dental and vision. Employees are covered at 75%. We offer a 401K after 6 months, we do not provide paid holidays or PTO, sick time is offered in accordance with local laws. This position is open until filled.

Job ID: 520250940
Originally Posted on: 5/7/2026

Want to find more Technology opportunities?

Check out the 165,238 verified Technology jobs on iHireTechnology