ML Compiler Intern: Auto-Tuning for PyTorch & Triton Kernels

Samsung Electronics America

San Jose (CA)

On-site

USD 39,000 - 94,000

Full time

5 days ago
Be an early applicant

A complete application in a minute

Tailored resume and cover letter, ready to send.

Get past ATS filters

Benefits offered by this job

Relocation Support
Housing Stipend
Give Back
Prioritize Emotional Wellness
Stay Fit
Embrace Flexibility

Job summary

Samsung Semiconductor seeks a summer ML compiler intern to design auto-tuning for PyTorch models on a compute-near-memory AI accelerator. You will develop a cost-guided search space for Triton kernel configs, tying it to torch.compile and Inductor autotuning.

Work closely with PyTorch/Triton teams to push LLM inference performance on memory-centric hardware. The role is onsite at the San Jose headquarters with a text-rich project plan, mentoring, and a focus on delivering measurable kernel-level

Qualifications

  • Pursuing a Masters or PhD in Computer Science, Computer Engineering or Electrical Engineering; PhD preferred.
  • Must have at least 1 academic quarter/semester remaining
  • Strong Python and C++, with experience writing or tuning Triton kernels or working with PyTorch compiler internals (torch.compile, FX, Inductor).
  • Grounding in compilers or performance engineering: IR and passes, cost models, roofline analysis and profiling.

Responsibilities

  • Design a search space for Triton kernel configurations on the accelerator: tile sizes, launch-grid mapping, on-chip buffer budgets and load style.
  • Build legality rules with compiler engineers that prune configurations that will not compile or fit in on-chip memory.
  • Develop a kernel cost model, calibrated against simulator and profiler, ranking candidates for benchmarking.
  • Build a reliable benchmarking harness and a persistent tuning cache to keep tuning cost practical.
  • Integrate the tuner with torch.compile Inductor autotuning path and with Triton’s autotuner.
  • Extend tuning to data placement: tune kernels for a given tensor layout and export tuned costs for placement passes.
  • Measure kernel-level and end-to-end LLM inference gains and share results in weekly syncs and final presentation.

Skills

Python
C++
PyTorch
Performance engineering

Education

Masters or PhD in Computer Science, Computer Engineering or Electrical Engineering

Tools

Triton kernels
Torch.compile
Inductor autotuning
LLVM

Job description

Samsung Semiconductor seeks a summer ML compiler intern to design auto-tuning for PyTorch models on a compute-near-memory AI accelerator. You will develop a cost-guided search space for Triton kernel configs, tying it to torch.compile and Inductor autotuning.

Work closely with PyTorch/Triton teams to push LLM inference performance on memory-centric hardware. The role is onsite at the San Jose headquarters with a text-rich project plan, mentoring, and a focus on delivering measurable kernel-level

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Intern ML Compiler for Auto-Tuning (PyTorch/Triton)
Intern ML Compiler for Auto-Tuning (PyTorch/Triton)

samsungsemiconductor • San Jose (CA)

On-site
USD 55,000 - 83,000
Medical/Dental/Vision
Inclusive rewards plan
Investment in your future
+2
Intern, ML Compiler (Kernel Auto-Tuning)
Intern, ML Compiler (Kernel Auto-Tuning)

samsungsemiconductor • San Jose (CA)

On-site
USD 55,000 - 83,000
Medical/Dental/Vision
Inclusive rewards plan
Investment in your future
+2
Staff Compiler Engineer, PyTorch — Hybrid/Onsite IR & DSL
Staff Compiler Engineer, PyTorch — Hybrid/Onsite IR & DSL

Samsung Electronics America • San Jose (CA)

On-site
USD 163,000 - 253,000
4+ weeks paid time off
Diverse benefits package for wellbeing
Support for family care and emotional wellness
Intern, ML Compiler (Kernel Auto-Tuning)
Intern, ML Compiler (Kernel Auto-Tuning)

Samsung Electronics America • San Jose (CA)

On-site
USD 39,000 - 94,000
Relocation Support
Housing Stipend
Give Back
+3
Senior AI Compiler Engineer - Triton & MLIR Expert
Senior AI Compiler Engineer - Triton & MLIR Expert

NVIDIA Corporation • United States

Remote
USD 184,000 - 288,000
Equity eligibility
Benefits package
ML Software Intern — AI Hardware & Model Optimization
ML Software Intern — AI Hardware & Model Optimization

TetraMem - Accelerate The World • San Jose (CA)

On-site
USD 48,000 - 62,000
ML Compiler Intern: Shape the Future of AI/ML
ML Compiler Intern: Shape the Future of AI/ML

samsungsemiconductor • San Jose (CA)

On-site
USD 55,000 - 83,000
Relocation Support
Housing Stipend
Charitable giving match
ML Compiler Intern: Autonomy HW & AI Optimizations
ML Compiler Intern: Autonomy HW & AI Optimizations

Rivian Automotive • Palo Alto (CA)

On-site
USD 62,000 - 70,000
Paid vacation
Paid sick leave
Medical insurance
Compiler Engineer - Kernelize
Compiler Engineer - Kernelize

kernelize • United States

Remote
USD 120,000 - 180,000
Fully remote
AI Systems Performance Intern — Benchmark & Profiling
AI Systems Performance Intern — Benchmark & Profiling

Samsung Electronics America • San Jose (CA)

On-site
USD 39,000 - 94,000
Relocation Support
Housing Stipend
Give Back programs
+2