GPU Software Engineer

Who We Are:  

• CAE Vision: Our vision is to be the worldwide partner of choice in defense and security, and civil aviation by revolutionizing our customers’ training and critical operations with digitally immersive solutions to elevate safety, efficiency and readiness.  

• CAE Defense & Security Mission: CAE's Defense and Security business unit focuses on helping prepare military customers to develop and maintain the highest levels of mission readiness.  

• CAE Values: Empowerment, Innovation, Excellence, Integrity and OneCAE make us who we are and we strive to make a difference in the world while helping each other succeed.  

What We Have to Offer:  

• Comprehensive and competitive benefits package and flexibility that promotes work-life balance  

• A work environment where all employees are valued, respected and safe  

• Freedom to succeed by enabling team members to deliver, take initiatives and make decisions  

• Recognition, professional development, advancement and having fun!  

Summary   

We are seeking a skilled GPU Software Engineer to join our growing AI & Data Science team in R&D. This role is ideal for someone passionate about parallel computing, (General-Purpose computing on Graphics Processing Units) GPGPU programming, and distributed systems to design and optimize high-performance applications. The ideal candidate will have a strong background in scalable architectures, GPU acceleration, and multi-node environments to deliver cutting-edge solutions for compute-intensive workloads.  This position is onsite with locations in Tampa FL, Arlington TX, or Orlando FL. 

Essential Duties and Responsibilities 

• Design and implement parallel algorithms for large-scale data processing and scientific computing. 

• Develop and optimize GPGPU applications using CUDA, OpenCL, or similar frameworks. 

• Architect and maintain distributed systems for high availability and fault tolerance. 

• Collaborate with cross-functional teams to integrate solutions into production environments. 

• Benchmark, profile, and tune performance across heterogeneous computing platforms. 

• Stay current with emerging technologies in GPU computing and distributed architectures. 

Qualifications and Education Requirements 

• Bachelor’s or Master’s degree in Computer Science, or related field. 

• 3+ years of experience in parallel programming, GPGPU computing, and distributed systems. 

• Strong understanding of parallel programming concepts, including multi-threading, synchronization, and communication. 

• Strong proficiency in C/C++, Python, and parallel programming paradigms. 

• Familiarity with virtualization technologies, such as Docker and Kubernetes. 

• Hands-on experience with CUDA, OpenCL, or HIP for GPU acceleration. 

• Solid understanding of distributed systems, networking, and cluster management tools (e.g., Kubernetes). 

• Experience with performance profiling and optimization techniques. 

• Understanding of data structures and algorithms, including object-oriented programming. 

• Excellent communication and collaboration skills. 

Preferred Skills 

• Device driver development, including GPU or CPU.