Startups · AI

AI Systems Performance Engineer

Broadcom · USA-CA San Jose Innovation Drive · On-site

← All jobs
About Broadcom

Broadcom delivers semiconductors and infrastructure software for global enterprises’ most complex, mission-critical needs.

About the role

1. If you are a first time user, please create your candidate login account before you apply for a job. (Click Sign In > Create Account) 2. If you already have a Candidate Account, please Sign-In before you apply. Found on 1752vc Careers, the job board for startup and VC roles.

What they're looking for

  • NIC / host networking: performance tuning or validation of high-speed NICs, drivers, or RDMA/RoCEv2
  • AI cluster building: bringing up and tuning multi-node GPU clusters, including collective communication libraries such as NCCL
  • Proven ability to diagnose root causes of performance problems in distributed systems
  • Preferred Qualifications
  • Experience in more than one of the three areas above
  • Experience with MLPerf Training or Inference
More about this role

1. If you are a first time user, please create your candidate login account before you apply for a job. (Click Sign In > Create Account)

2. If you already have a Candidate Account, please Sign-In before you apply.

Senior AI Network Performance Engineer (NIC / Host Networking)

We are seeking an experienced Senior AI Network Performance Engineer to join the Performance Lab within our Architecture group. You will benchmark AI inference, training, and storage workloads on GPU clusters, with a focus on NIC and host networking performance. Your reports will guide customers in deployment and help our marketing team position the product.

Your primary focus will be the server side of the network: the NIC, its drivers, and the host stack that connects AI workloads to the fabric. You will run rigorous benchmarks, isolate bottlenecks, and tune for maximum throughput and minimum latency. If you have gone deep on NIC performance, built or operated AI clusters, or run inference serving at scale, we want to hear from you.

Key Responsibilities

Benchmarking: Install, configure, and run AI performance benchmarks, including MLPerf (Training and Inference) and NCCL collective communication tests.

NIC...

Read the full posting on Broadcom's site ↗

Build your edge while you search

Free tools for founders and investors, plus VC Unfiltered, our take on startups, venture and the people who build them.