This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more.

Role Description

We're looking for an ML infrastructure engineer to bridge the gap between research and production at Runway. You'll work directly with our research teams to productionize cutting-edge generative models—taking checkpoints from training to staging to production, ensuring reliability at scale, and building the infrastructure that enables fast iteration.

You'll be embedded within research teams, providing platform support throughout the entire model development lifecycle. Your work will directly impact how quickly we can ship new models and features to millions of users.

A peek at our technical stack

• API endpoints for real-time collaboration and media asset management written in TypeScript, running in ECS containers on AWS Fargate.
• Leverage multiple AWS-native components, such as S3, CloudFront, Lambda, Kinesis, and SQS.
• Inference backend written in Python (PyTorch, TorchScript), deployed across multiple clusters/cloud providers.
• Use Kubernetes for container orchestration, with k8s-native components such as Flyte, Kueue, and Kyverno for efficient job orchestration.
• Invest in Prometheus and Grafana for monitoring, and Terraform to manage infrastructure.

Qualifications

• 4+ years of experience running ML model inference at scale in production environments.
• Strong experience with PyTorch and multi-GPU inference for large models.
• Experience with Kubernetes for ML workloads—deploying, scaling, and debugging GPU-based services.
• Comfortable working across multiple cloud providers and managing GPU driver compatibility.
• Experience with monitoring and observability for ML systems (errors, throughput, GPU utilization).
• Self-starter who can work embedded with research teams and move fast.
• Strong systems thinking and pragmatic approach to production reliability.
• Humility and open-mindedness; at Runway we love to learn from one another.

Requirements

• Experience building custom inference frameworks or serving systems (Nice to Have).
• Deep understanding of distributed training and inference patterns (FSDP, data parallelism, tensor parallelism) (Nice to Have).
• Ability to debug low-level issues: NCCL networking problems, CUDA errors, memory leaks, performance bottlenecks (Nice to Have).
• Experience with diffusion models or video generation systems (Nice to Have).
• Knowledge of real-time or latency-sensitive ML applications (Nice to Have).

Benefits

• Salary range: $240,000 - $290,000.
• Commitment to creating a space where employees can bring their full selves to work and have equal opportunity to succeed.

Company Description

Runway strives to recruit and retain exceptional talent from diverse backgrounds while ensuring pay equity for our team. Our salary ranges are based on competitive market rates for our size, stage, and industry, and salary is just one part of the overall compensation package we provide.

There are many factors that go into salary determinations, including relevant experience, skill level and qualifications assessed during the interview process, and maintaining internal equity with peers on the team. The range shared below is a general expectation for the function as posted, but we are also open to considering candidates who may be more or less experienced than outlined in the job description. In this case, we will communicate any updates in the expected salary range.

Lastly, the provided range is the expected salary for candidates in the U.S. Outside of those regions, there may be a change in the range, which again, will be communicated to candidates.

We're excited to be recognized as a best place to work by Crain's, InHerSight, BuiltIn NYC, and INC.