Beam
Ultrafast Inference for AI Products
Research Engineer
About the role
Beam helps developers build and run AI and LLM applications on serverless GPUs, without managing infrastructure. Hundreds of teams are using Beam to power their applications in production. And we have a thriving community of developers using our platform to build state-of-the-art apps with AI.
As a Research Engineer, you will solve difficult problems in distributed computing, storage, and runtime optimizations at scale. This involves developing creative solutions to difficult systems problems, and working with the rest of our team to put them into production.
Our current research streams involve things like:
- Low-level systems development: working with container runtimes, OCI image formats, and lazy-loading large files from content addressable storage
- Efficiently packing thousands of workloads into GPUs across multiple clouds
- Working with cutting-edge technologies, like GPU checkpoint restore and CRIU
This role is in-person/hybrid in New York. Please only apply if you can commit to working from the office at least 3 days week.
Skills & Experience
Requirements
- Experience working on hard or open-ended problems related to distributed systems, operating systems, storage, or networking
- Proven track record of independently owning projects from start to finish
- Strong systems level programming skills
- Experience writing a statically typed language, like Golang or Rust
- Enthusiasm for developer tools, cloud native technologies, and open source software
Nice-to-haves
- Familiarity with things like gRPC, Helm/Kustomize, and Terraform
- Experience with AI/ML and GPU programming
Benefits
- Competitive salary and meaningful equity
- Join a fast-growing pre-series A company at the ground floor
- Health, dental, and vision benefits with 90% coverage for you and 50% for dependents
- Opportunities to participate in events across the cloud native community
- Quarterly offsite trips, fitness stipend, learning budget, and much, more
About Beam
Beam is a tool to quickly build machine learning-powered applications. Our platform helps developers run their code on serverless GPUs, deploy highly performant APIs, and rapidly prototype ML models — without managing any infrastructure.
Machine learning is eating software, but it’s still difficult for developers to leverage ML in their products. Today, companies are spending months building their own ML platforms, or relying on outdated tools that were originally designed for academics.
We believe that for ML to reach widespread adoption, the underlying infrastructure needs to be hidden from the user. We're building the fastest way for developers to go from an ML prototype to a production service.
