Senior Inference Platform Architect - GPU Cloud (Equity)

Hamilton Barnes Associates Limited; San Francisco (CA); On-site; USD 270,000 - 330,000; Full time

Benefits offered by this job

Equity

Job summary

A technology recruitment agency seeks a professional to lead the architecture of a distributed inference platform within a stealth-mode hyperscale data center startup. Applicants must have over 5 years of experience with large-scale distributed systems and strong proficiency in languages such as Python, Go, or Rust, along with a solid understanding of GPU software stacks. This unique opportunity offers an annual salary of $300,000 and includes equity benefits.

Qualifications

• 5+ years’ experience building large-scale, fault-tolerant distributed systems.
• Strong understanding of GPU software stacks (CUDA, Triton, NCCL) and Kubernetes.
• Practical experience with model-serving frameworks such as vLLM, SGLang, TensorRT-LLM.

Responsibilities

• Take ownership of the inference platform architecture.
• Design, build, and optimise distributed inference systems.
• Integrate, tune, and operate inference engines across multiple model types.
• Develop APIs and orchestration layers for multi-tenant and dedicated deployments.

Skills

Building large-scale distributed systems

Proficiency in Python, Go, Rust

Understanding of GPU software stacks

Experience with model-serving frameworks

Knowledge of performance optimisation techniques

Familiarity with Infrastructure-as-Code tools

Job description

A technology recruitment agency seeks a professional to lead the architecture of a distributed inference platform within a stealth-mode hyperscale data center startup. Applicants must have over 5 years of experience with large-scale distributed systems and strong proficiency in languages such as Python, Go, or Rust, along with a solid understanding of GPU software stacks. This unique opportunity offers an annual salary of $300,000 and includes equity benefits.