CUDA & AI Systems Engineer — Flexible Hours

MWDN Ltd.

Lisboa

Remote

EUR 70,000 - 110,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

29 days PTO (national holidays)
10 paid recovery days
Free English classes
HR support

Job summary

MWDN Ltd. is a global IT outstaffing company with 23+ years of experience, connecting exceptional tech talent with leading companies across Israel, the USA, Great Britain, and Western Europe.

We are seeking a highly technical engineer or researcher with deep expertise in GPU computing, CUDA, and LLM inference optimization to work on AI systems and HPC challenges. This role suits those who enjoy understanding how things work under the hood—from GPU architecture and low-level kernels to LLM

Qualifications

  • Proven hands-on CUDA/GPU programming experience.
  • Deep understanding of GPU memory hierarchy and parallel execution.
  • Experience with LLM inference, AI systems or HPC.
  • Familiarity with frameworks such as vLLM, SGLang, TensorRT-LLM, Triton or FlashAttention.
  • Strong debugging of performance issues and low-level system behavior.
  • Excellent English communication.

Responsibilities

  • Investigate and optimize LLM inference performance on modern GPUs.
  • Work with inference and serving frameworks such as vLLM, SGLang, TensorRT-LLM, or similar systems.
  • Analyze GPU execution, memory access patterns, kernel performance, and inference bottlenecks.
  • Develop, optimize, debug, or reverse-engineer CUDA kernels and low-level GPU operations.
  • Explore optimization techniques for matrix multiplication, attention mechanisms, and neural network layers.
  • Benchmark performance and identify opportunities to improve latency, throughput, and GPU utilization.
  • Tackle technically challenging problems requiring hands-on experimentation.

Skills

CUDA programming
GPU architecture
LLM inference
English communication
problem solving
debugging performance

Education

PhD in CS/ML or related
Research experience

Tools

vLLM
SGLang
TensorRT-LLM
Triton
FlashAttention

Job description

MWDN Ltd. is a global IT outstaffing company with 23+ years of experience, connecting exceptional tech talent with leading companies across Israel, the USA, Great Britain, and Western Europe.

We are seeking a highly technical engineer or researcher with deep expertise in GPU computing, CUDA, and LLM inference optimization to work on AI systems and HPC challenges. This role suits those who enjoy understanding how things work under the hood—from GPU architecture and low-level kernels to LLM

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

GPU AI Engineer: CUDA & LLM Inference Optimizer
GPU AI Engineer: CUDA & LLM Inference Optimizer

MWDN Ltd. • Lisboa

On-site
EUR 70,000 - 110,000
Flexible working hours
29 days of PTO (18 working days per yr
10 paid recovery days
+5
CUDA / AI Engineer
CUDA / AI Engineer

MWDN Ltd. • Lisboa

Remote
EUR 70,000 - 110,000
29 days PTO (national holidays)
10 paid recovery days
Free English classes
+1
AI engineer for GPU programming
AI engineer for GPU programming

MWDN Ltd. • Lisboa

On-site
EUR 70,000 - 110,000
Flexible working hours
29 days of PTO (18 working days per yr
10 paid recovery days
+5
Remote GPU Kernel Engineer — CUDA/Triton Performance & Debugging
Remote GPU Kernel Engineer — CUDA/Triton Performance & Debugging

Anyone AI Inc. • Lisboa

Remote
EUR 85,000 - 158,000
GPU Kernel Engineer – CUDA, Triton & Accelerator Performance
GPU Kernel Engineer – CUDA, Triton & Accelerator Performance

Anyone AI Inc. • Lisboa

Remote
EUR 85,000 - 158,000
Senior Rust Developer — High-Performance, Flexible Hours
Senior Rust Developer — High-Performance, Flexible Hours

MWDN • Lisboa

On-site
EUR 99,354 - 147,612
PTO: 29 days
Flexible working hours
Full financial and legal support for i
+2
Lead ML Ops Engineer - Remote GPU Inference Platform
Lead ML Ops Engineer - Remote GPU Inference Platform

Pragmatike • Lisboa

Remote
EUR 90,000 - 130,000
Distributed Cloud | AI/ML Engineer
Distributed Cloud | AI/ML Engineer

Devoteam • Lisboa

On-site
EUR 60,000 - 90,000
Distributed Cloud AI/ML Engineer - LLM Ops & Production
Distributed Cloud AI/ML Engineer - LLM Ops & Production

Devoteam • Lisboa

On-site
EUR 60,000 - 90,000
Remote AI/ML Engineering Manager (Applied ML)
Remote AI/ML Engineering Manager (Applied ML)

SPD Technology • Portugal

Remote
EUR 90,000 - 130,000
Fully remote
Laptop provided
Licensed software
Top locations