Member of Technical Staff, Cloud Orchestration (Remote)
Inferact · Remote · Remote ·
COMPENSATION
$200k – $400k
Listed on the employer's job board (Ashby)
- Fully remote (worldwide)
- Kubernetes + Python/Rust/Go
- GPU cluster management
- Visa sponsorship available
- Pacific Time overlap
Join the team behind vLLM to engineer the operational backbone that supports massive-scale AI inference. You will design systems for cluster management, automation, and monitoring to ensure reliable model serving globally.
This position focuses on turning operational complexity into robust infrastructure, making deployments observable and recoverable for teams worldwide.
What you'll do
- Design systems for cluster management and deployment automation
- Implement production monitoring for large-scale AI services
- Ensure vLLM deployments are observable and debuggable
- Build infrastructure that enables frictionless model serving
- Create recoverable systems to handle operational complexity
What you'll need
- Bachelor's degree or equivalent in CS or engineering
- Strong experience with Kubernetes at scale
- Proven ability to design custom Kubernetes operators
- Proficiency in Python, Rust, or Go
- Experience with Terraform, Helm, or similar IaC tools
- Skill in managing GPU clusters and debugging hardware
- Ability to work across AWS, GCP, Azure, and on-prem
Nice to have
- Experience with Ray or Slurm orchestration tools
- Knowledge of GPU scheduling and resource optimization
- Familiarity with vLLM deployment patterns
- Track record in improving ML system reliability
- Experience with 1,000+ GPU cluster deployments
Stack
- vLLM
- Kubernetes
- Python
- Rust
- Go
- Terraform
- Helm
- AWS
- GCP
- Azure
- Ray
- Slurm
How you'll work
- Fully remote position open worldwide
- Timezone-flexible with Pacific Time overlap
- Regular syncs required for critical alignment
What you get
- Competitive salary and equity package
- Visa sponsorship available case-by-case
- Location-appropriate health coverage
- Benefits tailored to local market conditions