Senior ML Infra Engineer: Scalable AI Training Systems

Preference Model; Seattle (WA); On-site; USD 180,000 - 300,000; Full time

Benefits offered by this job

Health insurance

Vision insurance

Dental insurance

401K match

Lunch onsite

Weekly snacks

Job summary

Preference Model is seeking a Senior ML Infrastructure Engineer to build scalable systems powering post-training research on large language models. You will design compute, scheduling, and data infrastructure for in-house RL environments and maintain core ML framework primitives to accelerate experiments.

You will partner with Research Engineers to translate research needs into infrastructure requirements, ensuring reliability, low latency, and high throughput while scaling with cutting-edge AI

Qualifications

• Strong software engineering fundamentals for production-grade infra.
• Experience building ML/data-intensive infrastructure.
• Familiarity with ML frameworks such as PyTorch or JAX.

Responsibilities

• Design, build, and scale compute, scheduling, and data infrastructure for post-training research in in-house RL environments.
• Develop core ML framework primitives and internal tooling for reproducible experimentation.
• Build evaluation and benchmarking infra, monitoring, logging, and deployment systems to keep infra reliable as it scales.
• Collaborate with Research Engineers to translate research needs into infrastructure requirements and ship rapidly.

Skills

Software engineering

ML frameworks (PyTorch/JAX)

Distributed systems

Cloud platforms (AWS/GCP)

Kubernetes

Data pipelines

LLM training/inference basics

Infra reliability

Tools

JVM/CI tooling

Job description

Preference Model is seeking a Senior ML Infrastructure Engineer to build scalable systems powering post-training research on large language models. You will design compute, scheduling, and data infrastructure for in-house RL environments and maintain core ML framework primitives to accelerate experiments.

You will partner with Research Engineers to translate research needs into infrastructure requirements, ensuring reliability, low latency, and high throughput while scaling with cutting-edge AI