inferact - Member of Technical Staff, Cloud Orchestration

Singapore$200k - $200k+ Equity3mo ago

In Office Staff APAC Cloud Computing Cloud Engineer Rust Go Helm Python Terraform

Requirements

• Bachelor's degree or equivalent experience in computer science, engineering, or similar. • Strong experience with Kubernetes and container orchestration at scale. • Experience designing and implementing custom Kubernetes operators. • Proficiency in Python/Rust/Go and infrastructure-as-code tools (Terraform, Helm, etc). • Experience managing GPU clusters and debugging hardware issues. • Ability to work across cloud platforms (AWS, GCP, Azure) and on-premise infrastructure. • Experience with ML-specific orchestration tools (Ray, Slurm). • Knowledge of GPU scheduling, multi-tenancy, and resource optimization. • Familiarity with vLLM deployment patterns and configuration. • Track record of improving operational reliability for ML systems. • Experience deploying inference systems on large-scale GPU (1,000+) clusters. • Location: This role is based in Singapore. • Compensation: Depending on background, skills, and experience, the expected annual salary range for this position is S$200,000 to S$400,000 annually + equity. • Visa sponsorship: We sponsor visas on a case-by-case basis. • Benefits: Inferact offers a generous benefits package, including medical, dental, and vision coverage.

Benefits

• SGD 200K – SGD 400K • Offers Equity • Upload your resume here to autofill key application fields. • Drop your resume here! • Parsing your resume. Autofilling key fields... • (City, State, Country) • or drag and drop here • Please share a link to a personal project, open-source contribution, or technical blog post that you're most proud of or find most relevant to this role. • Your answer won't affect your candidacy. • If you require visa sponsorship, please share any relevant information on your current visa status and any potential timing considerations. • Scale numbers help us calibrate. Tell us what you owned rather than what the team owned. • Driver mismatches, missing GPUs, memory errors, NVLink or NVSwitch faults, node failures, scheduling failures, and vendor escalations all count. • Work, open source, and side projects all count. We care more about what you decided to do on your own judgment than about how large the project was.