Senior Software Engineer (AI Systems Performance)
Summary
Senior software engineer optimizing AI inference performance across large multi-GPU, multi-node compute clusters for a semiconductor/HPC project: benchmarking models, finding and fixing bottlenecks, and building monitoring and dashboarding tooling. Core stack is C++ and Python with Kubernetes/SLURM, Git, and Jenkins.
Join a leading semiconductor and high-performance computing project focused on accelerating next-generation AI workloads.
We are looking for a Senior Software Engineer (AI Systems Performance) to help optimize and scale AI inference across large GPU clusters and distributed environments. You will work alongside experts in AI, distributed systems, and GPU technologies, contributing to cutting-edge solutions used to benchmark, monitor, and improve the performance of modern AI models.
What you'll do
- Enable and benchmark AI models on large-scale distributed GPU systems
- Optimize AI inference workloads across multi-GPU and multi-node environments
- Develop solutions to improve throughput, latency, scalability, and reliability
- Collaborate with GPU library and infrastructure teams to identify and resolve performance bottlenecks
- Contribute to benchmarking frameworks, model management platforms, and monitoring solutions
- Build dashboards and tooling to track performance and system health
- Participate in performance analysis, debugging, automation, and quality improvements
What we're looking for
- Strong C++ and Python development skills
- Experience with AI inference, distributed systems, or high-performance computing
- Knowledge of performance analysis, optimization, and debugging techniques
- Experience working with large-scale compute clusters
- Familiarity with Kubernetes, SLURM, or similar orchestration platforms
- Experience with Git, CI/CD, and modern software engineering practices
Technologies
C++ • Python • AI/ML • Distributed Systems • Multi-GPU Computing • Kubernetes • SLURM • Git • Jenkins • Performance Engineering • High Performance Computing (HPC)
Why join?
✅ Work on cutting-edge AI and GPU technologies
✅ Solve complex performance and scalability challenges
✅ Collaborate with world-class engineers in AI and high-performance computing
✅ Influence the future of large-scale AI inference platforms
Ref: VR-125691
Skills
Sign in to read and join the discussion.