CUDA/GPU Developer

About the role

At IBM Software, we transform client challenges into solutions, building the world’s leading AI-powered, cloud-native products that shape the future of business and society. In this role, you’ll work on the GPU operator layer that enables accelerated analytics on GPU-accelerated lakehouse. You’ll help integrate GPU-aware execution into platform components and operators, with deep attention to kernel behavior, runtime efficiency, and productization on OpenShift.

Responsibilities

• Develop Component-Level Solutions: Design, code, and test innovative component-level software solutions, ensuring implemented solutions are unit tested and ready for integration.
• Contribute to CI/CD Pipeline: Help build and maintain the automated CI/CD pipeline that takes code through quality stages, ensuring seamless integration and delivery.
• Debug Customer-Reported Problems: Design, develop, and unit test code fixes for customer-reported issues, collaborating with stakeholders to resolve them efficiently.
• Deliver Offerings: Deliver high-quality software using leading-edge and proven technologies, meeting stakeholder requirements and expectations.
• Collaborate with Stakeholders: Work in an Agile, collaborative environment to understand requirements and provide input to ensure successful solution delivery.

Requirements

• Software Development & GPU-Aware Engineering: Experience designing, developing, testing, and delivering high-quality software solutions, including development for specific hardware targets and GPU programming for optimized performance.
• Systems-Level Debugging & Performance Optimization: Strong C++ and Linux debugging skills, with hands-on experience in performance profiling and optimization to identify bottlenecks.
• Component-Level Design & Problem Solving: Proven ability to design, code, and test component-level software solutions, ensuring unit testing and integration readiness.
• Agile Development & CI/CD Enablement: Experience working in Agile environments and contributing to CI/CD pipelines for continuous integration, testing, and delivery.
• Cross-Stack Development & Cloud-Native Familiarity: Ability to work across hardware and software boundaries, with familiarity in Kubernetes and OpenShift for scalable, containerized deployments.

Preferred Qualifications

• CUDA & GPU Data Processing Expertise: Hands-on experience with CUDA development and familiarity with GPU-accelerated data frameworks such as RAPIDS/cuDF.
• Performance Benchmarking & Observability: Experience with benchmarking and telemetry instrumentation to measure, analyze, and optimize system performance.
• Leading-Edge Technologies & Engineering Practices: Experience designing and delivering software using modern technologies across back-end and front-end layers, with exposure to DevOps practices.

Preferred Education: Bachelor's Degree