Member of Technical Staff, Kernel Engineering

INFERACT SINGAPORE PTE. LTD.; Penarth; On-site; GBP 99,000 - 198,000; Full time

Benefits offered by this job

Equity

Medical insurance

Dental insurance

Vision coverage

Job summary

Inferact is looking for a performance engineer to squeeze every FLOP from modern accelerators and to write kernels and low-level optimizations that power vLLM’s speed. Your code will run on hundreds of accelerator types, from NVIDIA GPUs to emerging silicon, and you’ll collaborate with hardware vendors to ensure maximum performance.

Fresh graduates are welcome to apply. Compensation includes equity and a comprehensive benefits package.

Qualifications

• Bachelor's degree in CS, engineering, or equivalent.
• 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 high-performance coding.
• Experience with profiling tools (Nsight, rocprof) and optimization methodologies.
• Obsession with benchmarks and squeezing every percentage point of speedup.

Responsibilities

• Write kernels and low-level optimizations for vLLM across accelerator types.
• Collaborate with hardware teams to maximize performance on new chips.
• Tune and profile code to achieve high FLOPS and efficiency.
• Contribute to architecture-aware optimizations and open-source components.

Skills

CUDA kernels

C++

Python

GPU architecture

Performance profiling

Benchmark optimization

Education

Bachelor's degree in Computer Science or Engineering

Tools

Nsight

rocprof

CuTeDSL

Triton

TileLang

Pallas

LLVM

MLIR

XLA

Job description

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

Fresh graduates are welcome to apply. Minimum years of work experience: 0.

Compensation: Monthly salary of S$15,000 to S$30,000, depending on background, skills, and experience, plus equity.

Benefits: Inferact offers a generous benefits package, including medical, dental, and vision coverage.