Infrastructure Inference Engineer for Scalable AI

Bison; San Francisco (CA); Presencial; USD 400.000 - 500.000; Jornada completa

Ventajas ofrecidas por este puesto de trabajo

Health, dental, and vision benefits

Unlimited PTO

Paid parental leave

Relocation support

Descripción de la vacante

Thinking Machines, based in San Francisco, CA, seeks an infrastructure research engineer to design, optimize, and scale systems powering large AI models. You will improve inference speed, cost-effectiveness, reliability, and reproducibility to accelerate model capabilities.

You’ll work with researchers and engineers to deploy cutting-edge AI models, extend orchestration (Kubernetes, Ray, SLURM) for distributed inference, and publish learnings to advance scalable AI infrastructure.

Formación

• Bachelor’s degree in computer science, engineering, or related field.
• Experience with deep learning frameworks and system architectures.
• Exposure to inference serving systems optimized for latency and throughput.
• Collaborative experience with cross-functional teams.
• Proactive, action-oriented mindset across multiple stacks.
• Strong coding and debugging skills in complex codebases.

Responsabilidades

• Collaborate with researchers and engineers to productionize cutting-edge AI models.
• Enable high-performance inference for new architectures.
• Design and implement tooling to improve performance, latency, and throughput.
• Optimize codebase and compute fleets (GPUs) for better utilization.
• Extend orchestration frameworks for distributed inference and large-batch serving.
• Establish reliability, observability, and reproducibility across the inference stack.
• Publish learnings through internal docs, open-source libraries, or reports.

Conocimientos

Deep learning frameworks

Inference serving

Collaboration

Initiative

Debugging

Educación

Bachelor’s degree or equivalent

Herramientas

PyTorch

JAX

SGLang

vLLM

Kubernetes

Ray

SLURM

Descripción del empleo

Thinking Machines, based in San Francisco, CA, seeks an infrastructure research engineer to design, optimize, and scale systems powering large AI models. You will improve inference speed, cost-effectiveness, reliability, and reproducibility to accelerate model capabilities.

You’ll work with researchers and engineers to deploy cutting-edge AI models, extend orchestration (Kubernetes, Ray, SLURM) for distributed inference, and publish learnings to advance scalable AI infrastructure.