CUDA Engineer
Employment Information
Report this job
Job expired or something wrong with this job?
Job Description
CUDA Engineer optimizing GPU kernels and LLM inference performance for MWDN, a global IT outstaffing company. Improving latency, throughput, and GPU utilization on modern GPUs.
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
- Work on technically challenging problems requiring analytical thinking and hands-on experimentation
Requirements:
- Strong hands-on experience with CUDA and GPU programming
- Deep understanding of GPU architecture, memory hierarchy, parallel execution, and performance optimization
- Experience with LLM inference, AI systems, GPU kernels, or high-performance computing
- Familiarity with vLLM, SGLang, TensorRT-LLM, Triton, or FlashAttention
- Experience debugging complex performance issues and investigating low-level system behavior
- Strong problem-solving skills
- Ability to communicate complex technical concepts in English
- PhD or research experience in Computer Science, Machine Learning, Computer Architecture, or a related field (nice to have)
- Publications, research projects, or meaningful contributions to open-source GPU/LLM infrastructure (nice to have)
- Experience with PyTorch internals, distributed inference, quantization, KV cache optimization, or custom GPU kernels (nice to have)
- Contributions to vLLM, SGLang, Triton, FlashAttention, or related repositories (nice to have)
Benefits:
- Security through careful client vetting to minimize risks and ensure reliable, timely payments
- Career support and assistance finding new opportunities if a project is not the right fit
- Legal assistance with independent contractor or sole proprietorship status, taxes, and related processes
- English courses and professional growth opportunities
- Team-building events
- Flexible working hours
- 29 days of PTO (18 working days per year plus all national holidays)
- 10 paid recovery days
- Full financial and legal support for independent contractors
- Free English classes with native speakers or Ukrainian teachers
- Dedicated HR support
Similar Jobs
CUDA Engineer
CUDA Engineer optimizing GPU kernels and LLM inference performance for MWDN, a global IT outstaffing company. Benchmarking modern GPUs, inference frameworks, and low-level systems.
CUDA Engineer
CUDA Engineer optimizing GPU kernels and LLM inference performance for MWDN, a global IT outstaffing company. Improving latency, throughput, and GPU utilization on modern systems.
CUDA Engineer
CUDA Engineer optimizing GPU kernels and LLM inference performance for MWDN, a global IT outstaffing company. Improving latency, throughput, and GPU utilization on modern hardware.
CUDA Engineer
CUDA Engineer optimizing GPU kernels and LLM inference performance for MWDN, a global IT outstaffing company. Benchmarking modern GPUs and improving latency, throughput, and utilization.
CUDA Engineer
CUDA Engineer optimizing GPU kernels and LLM inference performance for MWDN, a global IT outstaffing company. Improving latency, throughput, and GPU utilization on modern systems.
CUDA Engineer
CUDA Engineer optimizing GPU kernels and LLM inference performance for MWDN, a global IT outstaffing company. Improving latency, throughput, and GPU utilization on modern systems.
CUDA Engineer
CUDA Engineer optimizing GPU kernels and LLM inference performance on modern GPUs. Supporting international AI systems and high-performance computing projects through MWDN.
Senior Server Tech Services Engineer
Senior engineer resolving high-severity hardware and network issues across Akamai’s distributed cloud-edge platform. Leading escalations, repairs, and operational excellence for CDN and Internet Security products.
Associate Energy Engineer
Associate Energy Engineer analyzing building energy use and supporting modeling, audits, and project development. Contributing to Ameresco’s infrastructure modernization and sustainability solutions.
Forward Deployed Engineer
Forward Deployed Engineer building AI production systems for Lunon’s client companies. Owning deployments, integrations, reliability, and client handoffs end to end.
IAM Engineer – Level 3
IAM Engineer leading SailPoint, Okta, and AI governance automation for Brazil identity operations. Driving provisioning, compliance, remediation, and local team mentorship.
Senior Fire Engineer
Senior Fire Engineer leading PAS 9980 FRAEWs, fire strategies and remediation advice. Supporting Airey Miller, a UK property and construction consultancy, on complex building projects.
Lead Professional Services Engineer, Actimize
Lead Professional Services Engineer deploying NICE analytics software across cloud and on-premise environments. Troubleshooting enterprise systems and enabling data-driven customer experiences.
Senior Requirements Engineer
Senior Requirements Engineer developing EMS, PCS, and cybersecurity requirements for Canadian Solar’s utility-scale battery storage systems. Ensuring global compliance, certification readiness, and traceable requirements management.
Senior Requirements Engineer
Senior Requirements Engineer developing EMS, PCS, and cybersecurity requirements for e-STORAGE’s utility-scale battery storage systems. Ensuring global standards compliance across renewable energy projects.
Senior Narrative Engineer
Senior Narrative Engineer building dialogue, quest, and branching narrative systems in Unreal Engine. Supporting co-op multiplayer storytelling, VO, subtitles, and localisation pipelines.
Senior Tools Engineer
Senior Tools Engineer building Unreal Engine editor tools and content pipelines. Supporting art, audio, narrative, and multiplayer game production at Airship.
Senior Forward Deployed Engineer
Senior Forward Deployed Engineer building and deploying Databricks data and AI solutions for customers. Owning architecture, technical delivery, and customer-facing implementation across data engineering and ML/AI.
Vulnerability Management Engineer
Vulnerability Management Engineer driving risk-based exposure management across Backblaze’s open cloud storage infrastructure. Correlating threat intelligence, asset data, and exploitability to prioritize remediation.
Staff Project Engineer – Grid Scale
Staff Project Engineer leading grid-scale power-system design and commissioning. Mainspring manufactures fuel-flexible, low-emissions local power solutions.