Remote Generalist Engineer - AI Inference & Systems

Inferact; United States; Remote; USD 150,000 - 230,000; Full time

Benefits offered by this job

Health coverage

Global remote work

Visa sponsorship considered

Job summary

Inferact is growing vLLM as the world’s AI inference engine. We seek exceptional generalist engineers who own end-to-end infrastructure, from CUDA kernels to distributed systems, in a globally remote setting.

You’ll work autonomously, across time zones, and directly impact AI inference performance at scale. You’ll focus on inference runtime, kernel engineering, distributed performance, and cloud orchestration, with visa sponsorship considered on a case-by-case basis.

Qualifications

• Bachelor's degree or equivalent in computer science, engineering, or related field.
• Autonomous, self-directed work style with a track record of shipping.
• Excellent asynchronous communication across time zones.
• Strong track record of delivering high-impact work in complex technical environments.
• Expertise in at least one of: systems programming, GPU/accelerator programming, distributed systems, or ML infrastructure.

Responsibilities

• Own critical infrastructure and ship features end-to-end.
• Work across the vLLM stack from GPUs to distributed systems.
• Optimize CUDA kernels and design distributed orchestration.
• Build cloud orchestration, deployment automation, and production monitoring.

Skills

CUDA kernels

Distributed systems

Python (PyTorch)

Kubernetes

Transformer models

Education

Bachelor's degree

Job description

Inferact is growing vLLM as the world’s AI inference engine. We seek exceptional generalist engineers who own end-to-end infrastructure, from CUDA kernels to distributed systems, in a globally remote setting.

You’ll work autonomously, across time zones, and directly impact AI inference performance at scale. You’ll focus on inference runtime, kernel engineering, distributed performance, and cloud orchestration, with visa sponsorship considered on a case-by-case basis.