Principal Software Engineer – E2E Performance, Goodput

πŸ•’ November 7

Where this job comes from

Posted on NVIDIA's careers page β†—NVIDIA's careers page, not through a job board

First seen by Remote Rocketship November 7

Still open on NVIDIA's site. Checked 1 hour ago.

Apply Now
Logo of NVIDIA

NVIDIA

10,000+ employees

Founded 1993

πŸ₯ Healthcare

🏭 Manufacturing

πŸ€– Artificial Intelligence

Healthcare β€’ Manufacturing β€’ Artificial Intelligence

NVIDIA is a leading technology company specializing in accelerated computing and artificial intelligence. NVIDIA pioneers advancements in graphical processing units (GPUs), cloud computing, data centers, and virtual reality, with a focus on gaming, automotive, healthcare, and robotics industries. The company's innovations, such as NVIDIA Omniverse, transform traditional digital processes by enabling high-fidelity simulations and rendering tasks. Their applications span various industries, from autonomous vehicles using NVIDIA DRIVE to healthcare solutions with NVIDIA Clara, and AI-driven analytics and workflows.

πŸ“‹ Description

β€’ Drive performance characterization work streams with engineering teams of key CSP/hyperscale customers, ensuring understanding of platform performance expectations, profiling methodology, and tuning options for specific workloads β€’ Gather and synthesize CSP performance feedback, identify gaps between expected and actual throughput, and champion optimization priorities to NVIDIA's CUDA, NCCL, driver, and firmware teams β€’ Ensure open-source performance and stress tools such as STREAM, GPU Burn, and GPU BLAST are updated and validated for the latest NVIDIA rack-scale systems, GPU architectures, and CPU platforms β€’ Work with CSPs to ensure their performance and validation tooling reflects the latest GPU capabilities, memory hierarchy changes, and platform-specific tuning parameters β€’ Conduct cross-CSP performance comparison and pattern analysis to identify configuration, software, or workload differences explaining deployment performance gaps β€’ Collaborate with CSPs to prepare profiling infrastructure, benchmark harnesses, and configuration validation for deployment milestones β€’ Define test strategies and tooling requirements for performance validation for NVIDIA internal certification and customer acceptance

🎯 Requirements

β€’ 15+ years of experience in systems performance engineering, ideally in GPU/HPC/ML infrastructure β€’ BS or MS in Computer Science, Computer Engineering, or related field (or equivalent experience) β€’ Proficiency in GPU workload profiling: nsight systems, nsight compute, DCGM metrics, or equivalent instrumentation β€’ Understanding of distributed training performance dynamics: computation/communication overlap, pipeline bubbles, memory bandwidth utilization, collective efficiency β€’ Statistical methods for performance analysis: regression detection, confidence intervals, A/B comparison at scale β€’ Understanding of how the full software stack impacts performance: driver overhead, collective algorithm selection, memory allocation, scheduling, firmware power management β€’ Strong data analysis and visualization skills (Python, pandas, dashboards) β€’ Ability to communicate performance findings to both deep technical audiences and executive leadership β€’ Demonstrated success influencing multiple engineering teams to prioritize performance improvements β€’ Experience profiling and optimizing distributed training at 1000+ GPU scale (Megatron-LM, DeepSpeed, FSDP) β€’ Background in ML infrastructure performance at a CSP/hyperscaler β€’ Familiarity with NVIDIA platforms (DGX, HGX, NVLink topology) and profiling tools β€’ Experience building automated performance regression detection systems for production environments β€’ Understanding of inference workload performance dynamics (vLLM, TensorRT-LLM, SGLang, continuous batching)

πŸ–οΈ Benefits

β€’ Equity β€’ Benefits

Apply Now

πŸ“Š Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Similar Jobs

πŸ•’ November 7

8th Light

51 - 200

πŸ’Ό Consulting

πŸ“£ Marketing

Principal Software Engineer building scalable AI platforms and software solutions for 8th Light’s consulting clients. Advising executives, leading architecture, and coaching engineering teams.

πŸ•’ November 6

MOXFIVE

11 - 50

πŸ’Ό Consulting

πŸ₯ Healthcare

πŸ›‘οΈ Insurance

Staff Engineer building MOXFIVE's AI-powered cyber investigation platform. Designing agent capabilities, evaluations, distributed systems, and resilient data infrastructure.

πŸ•’ November 6

First Corporate Solutions, Inc.

51 - 200

βš–οΈ Legal

πŸ’Ό Consulting

πŸ›‘οΈ Insurance

Senior Software Engineer building full-stack software and infrastructure for Ficoso’s in-house web applications. Owning architecture, cloud services, CI/CD, security, and end-to-end feature delivery.

πŸ•’ November 6

Chainguard

51 - 200

πŸ” Security

☁️ SaaS

πŸ”’ Cybersecurity

Staff Software Engineer shaping Chainguard Harness, an AI-powered product that finds exploitable vulnerabilities in customer applications. Owning secure, scalable architecture for Chainguard’s software supply-chain security platform.

πŸ•’ November 6

GridUnity

51 - 200

⚑ Energy

☁️ SaaS

πŸ”Œ API

Staff Software Engineer building production AI workflows for GridUnity’s grid interconnection software. Leading reliable, customer-facing automation for utilities and grid stakeholders.

Built byΒ Lior Neu-ner. I'd love to hear your feedback β€” Get in touch via DM or support@remoterocketship.com
Follow Remote Rocketship on LinkedInFollow Remote Rocketship on InstagramFollow Remote Rocketship on FacebookFollow Remote Rocketship on TikTok