AI job summary
MWDN, an IT and software company, is looking for a CUDA / AI Engineer to investigate and optimize LLM inference performance on modern GPUs. Candidates need strong hands-on experience with CUDA and GPU programming, a deep understanding of GPU architecture and memory hierarchy, familiarity with frameworks such as vLLM, TensorRT-LLM, or Triton, and the ability to communicate complex technical concepts in English. PhD or research experience in Computer Science or a related field is a plus. The position includes a paid training budget.
Job description
- 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.
- Work on technically challenging problems requiring strong analytical thinking and hands-on experimentation.
We’re looking for a highly technical engineer or researcher with deep expertise in GPU computing, CUDA, and LLM inference optimization to work on challenging problems at the intersection of AI systems and high-performance computing.
This opportunity is ideal for someone who enjoys understanding how things work under the hood — from GPU architecture and low-level kernels to LLM inference engines and performance bottlenecks.
Similar jobs
- Full-time
- Cyprus
- Full-time
- Cyprus
- Senior
- Full-time
- Cyprus
- Mid
- Full-time
- Limassol, Cyprus
- Full-time
- Limassol, Cyprus
- Mid
- Full-time
- Countrywide, Cyprus
- Mid
- Full-time
- Countrywide, Cyprus
- Full-time
- Nicosia, Cyprus
- Junior