GPU Engineer - Contract - Remote

Skillsearch Enterprise Technology; Novara; Remoto; EUR 40.000 - 60.000; Part-time

Descrizione del lavoro

A technology consulting company is seeking a GPU Engineer to work remotely until the end of 2025. You'll be responsible for optimizing GPU workloads, implementing monitoring solutions, and automating processes. The ideal candidate has at least 2 years of experience in GPU engineering, with expertise in CUDA and related tools. This role offers a chance to work with cutting-edge technologies in a collaborative and agile environment.

Competenze

• Minimum 2 years experience in GPU engineering or cloud-based GPU workload optimization.
• Experience with Infrastructure as Code for automated resource management.
• Strong analytical and problem-solving skills.

Mansioni

• Optimize performance of applications using GPU parallelization.
• Analyze deployment methods for GPU frameworks.
• Implement active GPU monitoring and establish dashboards.

Conoscenze

GPU services management

GPU software development

Performance benchmarking

Infrastructure as Code

CI/CD pipeline implementation

Kubernetes

Scripting (Python, Bash)

Strumenti

CUDA

TensorFlow

NVIDIA Triton Inference Server

Terraform

Prometheus

Grafana

Descrizione del lavoro

Overview

Our client, part of the UN, are looking to hire a contract GPU Engineer initially until the end of 2025. It's a fully remote position.

About the Role

You will conduct comprehensive performance benchmarking, profiling, and tuning of GPU workloads to provide evidence-based recommendations on suitable GPU sharing techniques.

Responsibilities

• Optimize performance of existing and new applications by leveraging GPU parallelization, identifying bottlenecks, and deploying code and framework-level improvements.
• Perform a thorough analysis of the deployment methods for GPU-accelerated serving frameworks in the market, with reference implementations and best-practice recommendations for large-scale serving solutions (e.g., NVIDIA Triton Inference Server, TensorRT, ONNX Runtime).
• Develop repeatable and automated configuration templates for GPU resources.
• Implement active GPU monitoring, including review and analysis of all relevant metrics (utilization, memory bandwidth, power, temperature, etc.), and establish dashboards and alerts for proactive performance and health management.
• Integrate GPU resource provisioning and configuration into CI / CD pipelines using Infrastructure as Code (IaC) tools (e.g., Terraform, Helm Charts, etc.), and document workflows for seamless deployment and rollback.
• Document all configurations, testing results, benchmarking analyses, and deployment procedures to ensure transparency and reproducibility.
• Establish active GPU monitoring protocols, including the identification and evaluation of available metrics, to select the most relevant indicators for ongoing performance management.
• Support self-service deployment of Large Language Models (LLMs) on GPU resources, enabling application owners with varying technical expertise to access and utilize GPU capabilities seamlessly.

Qualifications

Minimum 2 years of hands-on experience in GPU engineering or cloud-based GPU workload optimization, ideally within enterprise or large-scale environments. NVIDIA Certified (Preferred).

Required Skills

• Direct experience with GPU services, including resource provisioning, scaling, and optimization.
• Demonstrable expertise in GPU-accelerated software development (CUDA, OpenCL, TensorRT, PyTorch, TensorFlow, ONNX, etc.).
• Strong background in performance benchmarking, profiling (Nsight, nvprof, or similar tools), and workload tuning.
• Experience with Infrastructure as Code (Terraform, HELM Charts, or equivalent) for automated cloud resource management.
• Proven experience designing and implementing CI / CD pipelines for GPU-enabled applications using tools like GitHub Actions (Preferred) or similar.
• Working knowledge of Kubernetes and GPU scheduling, including setup of GPU-enabled clusters and deployment of GPU workloads in Kubernetes.
• Familiarity with GPU monitoring and observability, using tools such as Prometheus, Grafana, NVIDIA Data Center GPU Manager (DCGM), or custom scripts.
• Proven ability to analyze deployment approaches for GPU-accelerated serving frameworks and deliver reference implementations.
• Experience implementing software quality engineering practices (unit testing, code review, test automation, reproducibility).
• Strong scripting skills in Python, Bash, or PowerShell for automation and monitoring purposes.
• Excellent analytical, problem solving, and troubleshooting abilities. Quick learner, adaptable to evolving requirements and emerging GPU / cloud technologies. Positive and collaborative attitude in Agile environments.