Member of Technical Staff, Kernel Engineering
- Salary
- $200K - $400K
- Level
- Staff
- Work type
- On-site · Singapore
- Visa
- Sponsors visas
Open. First seen 2 October 2026.
About the role
Inferact's standard text
Inferact's mission is to grow vLLM as the world's AI inference engine and accelerate AI progress by making inference cheaper and faster. Founded by the creators and core maintainers of vLLM, we sit at the intersection of models and hardware—a position that took years to build.
About the Role
We're looking for a performance engineer to squeeze every FLOP out of modern accelerators. You'll write the kernels and low-level optimizations that make vLLM the fastest inference engine in the world. Your code will run on hundreds of accelerator types, from NVIDIA GPUs to emerging silicon. When hardware vendors develop new chips, they integrate with vLLM. You'll work directly with these teams to ensure we're extracting maximum performance from every generation of hardware.
Skills and Qualifications
Minimum qualifications:
- Bachelor's degree or equivalent experience in computer science, engineering, or similar.
- Deep experience writing CUDA kernels or equivalent (CuTeDSL, Triton, TileLang, Pallas).
- Strong understanding of GPU architecture: memory hierarchy, warp scheduling, tiling, tensor cores.
- Proficiency in C++ and Python with demonstrated ability to write high-performance code.
- Experience with profiling tools (Nsight, rocprof) and performance optimization methodologies.
- Obsession with benchmarks and squeezing every percentage point of speedup.
Preferred qualifications:
- Experience with ML-specific kernel optimization (FlashAttention, fused kernels).
- Knowledge of quantization techniques (INT8, FP8, mixed-precision).
- Familiarity with multiple accelerator platforms (NVIDIA, AMD, TPU, Intel).
- Experience with compiler technologies (LLVM, MLIR, XLA).
Bonus points if you have:
- Kernel-related contributions to vLLM or other inference engine projects.
- Contributions to open-source GPU, ML systems, or compiler optimization projects
- Written deep technical blogs on GPU optimization.
Logistics
- Location: This role is based in Singapore.
- Compensation: Depending on background, skills, and experience, the expected annual salary range for this position is S$200,000 to S$400,000 annually + equity.
- Visa sponsorship: We sponsor visas on a case-by-case basis.
- Benefits: Inferact offers a generous benefits package, including medical, dental, and vision coverage.
What this role asks for
85% of this description is written for the role. The rest is Inferact's standard text, folded away below.
Read against Inferact's other open postings on this site.
The team: Research & Engineering HIRES STEADILY
This role is one of 23 open in Research & Engineering. 5 were posted in the last 30 days and the oldest in January: a team that hires all year rather than one being built.
WHAT THE TEAM WORKS WITH, ACROSS ITS POSTINGS
Python (14 of 23), LLM (11 of 23), PyTorch (11 of 23), Kubernetes (10 of 23), Golang (9 of 23), Machine Learning (8 of 23), CUDA (7 of 23)
OTHER ROLES ON THIS TEAM
- Engineering Manager posted Oct 14
- Member of Technical Staff, Vulnerability Management posted Oct 2
- Member of Technical Staff, Forward Deployed Engineer posted Oct 2
- Member of Technical Staff, Supercomputing Infrastructure posted Sep 24
- Member of Technical Staff, Production Site Reliability Engineer posted Sep 22
- Inference Engineering, Co-op posted Sep 15
- Member of Technical Staff, Inference posted Sep 4
- Member of Technical Staff, Cloud Orchestration (Remote) posted Aug 25
- Member of Technical Staff, Supercomputing Infrastructure posted Aug 21
- Member of Technical Staff, AMD GPU Performance Engineering posted Jun 26
- Member of Technical Staff, TPU Performance Engineering posted Jun 26
- Member of Technical Staff, AMD GPU Performance Engineering posted Jun 25
- Member of Technical Staff, Performance and Scale posted Jun 24
- Member of Technical Staff, Inference posted Jun 24
- Member of Technical Staff, Cloud Orchestration posted Jun 24
- Member of Technical Staff, Inference posted Jun 18
- Member of Technical Staff, Developer Relations posted Jun 17
- Member of Technical Staff, TPU Performance Engineering posted Jun 17
- Member of Technical Staff, Exceptional Generalist (Remote) posted Jan 22
- Member of Technical Staff, Cloud Orchestration posted Jan 22
- Member of Technical Staff, Kernel Engineering posted Jan 22
- Member of Technical Staff, Performance and Scale posted Jan 22
From the team and dates on Inferact's own job board.
Similar jobs
- Member of Technical Staff - Inference at Ghost
Shares 3 skills: CUDA, C++, Python · Staff level - Member of Technical Staff - ML Infra at Trajectory
Shares 3 skills: CUDA, C++, Python · Staff level - Senior Manager, AI Deployment at General Motors
Shares 3 skills: CUDA, C++, Python - Senior DSP Engineer at Axon
Shares 3 skills: CUDA, C++, Python - Technical Lead Simulation Engineering_SIL/HIL, Cuda/Opencl at Aptiv
Shares 3 skills: CUDA, C++, Python - Engineering Manager at Inferact
Also at this company
Is this your posting and you want it taken down? Email info@careerholo.com.