LLM Inference Operator/Compiler Performance Engineer

Zhiye

Singapore

On-site

SGD 120,000 - 180,000

Full time

15 hours ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Job summary

Zhiye in Singapore is hiring a Campus Singapore-LPU Operator / Compiler / Performance Engineer to build LLM inference software for the Language Processing Unit. You will develop and optimize inference operators and compiler lowerings, focusing on performance across tensor shapes and precisions.

Your work includes profiling, code generation, and co-design with architecture and runtime teams to balance compiler scheduling, operator implementations, and hardware utilization.

Qualifications

  • PhD in CS, EE, Automation or related fields; exceptional final-year Master’s candidates welcome.

Responsibilities

  • Develop and optimize inference operators/kernels (GEMM, attention).
  • Implement lowering from tensor graphs to LPU ISA: fusion, buffers, scheduling, codegen.
  • Run microbenchmarks and profiling to identify bottlenecks and improve latency/throughput.
  • Co-design with architecture and runtime teams and add workloads to regression tests.

Skills

C/C++
Python scripting
Linux tooling
Parallelism

Education

PhD in CS/EE/Automation

Tools

LLVM
MLIR
TVM
Triton
CUDA

Job description

Zhiye in Singapore is hiring a Campus Singapore-LPU Operator / Compiler / Performance Engineer to build LLM inference software for the Language Processing Unit. You will develop and optimize inference operators and compiler lowerings, focusing on performance across tensor shapes and precisions.

Your work includes profiling, code generation, and co-design with architecture and runtime teams to balance compiler scheduling, operator implementations, and hardware utilization.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Campus Singapore-LPU Operator / Compiler / Performance Engineer
Campus Singapore-LPU Operator / Compiler / Performance Engineer

Zhiye • Singapore

On-site
SGD 120,000 - 180,000
LLM Inference Optimization Engineer (GPU)
LLM Inference Optimization Engineer (GPU)

Rakuten Asia Pte Ltd • Singapore

On-site
SGD 120,000 - 180,000
Senior LLM Inference Performance Engineer
Senior LLM Inference Performance Engineer

Bitdeer Technologies Group • Singapore

On-site
SGD 120,000 - 180,000
Welfare benefits
Training and mentoring
AI Accelerator Co-Design Engineer (HW-SW)
AI Accelerator Co-Design Engineer (HW-SW)

Zhiye • Singapore

On-site
SGD 90,000 - 120,000
LLM Inference Performance Engineer
LLM Inference Performance Engineer

Bitdeer Technologies Group • Singapore

On-site
SGD 120,000 - 180,000
LLM Post-Training Research Engineer
LLM Post-Training Research Engineer

Manus AI • Singapore

On-site
SGD 120,000 - 200,000
Equity & Shared success
Unlimited Manus Tokens
Multilingual LLM Engineer: Training, Tuning & Deployment
Multilingual LLM Engineer: Training, Tuning & Deployment

Nanyang Technological University • Singapore

On-site
SGD 120,000 - 190,000
Campus Singapore-AI Hardware-Software Co-design Engineer
Campus Singapore-AI Hardware-Software Co-design Engineer

Zhiye • Singapore

On-site
SGD 90,000 - 120,000
LLM & GPU Scale Engineer - AI Infra (Stock Options)
LLM & GPU Scale Engineer - AI Infra (Stock Options)

TikTok Inc. • Singapore

On-site
SGD 60,000 - 90,000
Yoga and fitness
Stock options
Positive team atmosphere
+7
LLM & AI Research Scientist
LLM & AI Research Scientist

6Estates - Enterprise AI Solutions • Singapore

On-site
SGD 70,000 - 110,000