Principal Engineer, On-Device Inference & GPU Kernels
Ort: Wrocław, Warsaw, Poland (Hybrid) · Bereich: Engineering & Softwareentwicklung · Level: Lead · Veröffentlicht: 16. November 2026 · Geprüft: 16. Nov. 2026
Rollenübersicht & Beschreibung
Team-Wachstum & Marktbewegung von Opera beobachten
Polaris7 aggregiert offene Vakanzen, strategische Marktbewegungen und M&A-Signale in Echtzeit. Erhalte automatische Signal-Briefings zu Opera und vergleiche das Ökosystem mit direkten Wettbewerbern.
Opera
opera.comOpera ist ein führendes Technologieunternehmen für Webbrowser, programmatische Werbung und Gaming-Software.
Vollständiges Unternehmensprofil, Wettbewerber & Marktsignale zu Opera freischalten
Ähnliche Positionen im DACH-Ökosystem
Verwandte Rollen und Profile aus dem AdTech-, Media- und Datenmarkt
This role focuses on optimizing the performance of AI model inference systems. The engineer will work on low-level performance tuning, kernel optimization, and latency reduction for mission-critical AI workloads. Key challenges include maximizing GPU utilization and building high-throughput serving infrastructure.
Optimizes inference and training performance for large generative world models, profiling and eliminating bottlenecks in kernels, serving paths, and GPU utilization. Writes and tunes GPU kernels (CUDA/Triton), implements low-precision execution (FP8/INT8), and builds performance models and observability frameworks. Requires deep GPU programming experience, strong performance engineering foundations, and proficiency in Python with C++/CUDA capabilities.
This role designs, builds, and optimizes massive GPU clusters for extreme-scale training and inference workloads. The engineer develops and tunes low-level CUDA kernels using CUTLASS, Tensor Cores, and Nsight, profiling and eliminating bottlenecks across GPU memory hierarchy and networking, requiring 5+ years of low-level system programming in C/C++ and experience with large-scale GPU clusters.
This Kernel Engineer role at an AI company focuses on making machine learning training and inference faster, more efficient, and more reliable at the hardware-software boundary. The engineer will specialize in GPU/accelerator kernels, ML compilers, or framework/runtime and inference performance, optimizing compute primitives, memory layouts, and code generation. The role requires deep implementation-level expertise in stacks like CUDA, Triton, XLA, or PyTorch/JAX backends.
Weitere Positionen bei Opera
3 weitere offene Stellen
This role provides operational support for Opera's advertising technology products, focusing on campaign delivery, optimization, ad trafficking, and troubleshooting within the AdTech ecosystem. The specialist ensures smooth campaign execution and resolves issues to maximize performance.
This role leads security and model internals for AI systems within Opera's AI & Browser Innovation Hub. The principal engineer will focus on securing AI models and understanding their internal workings, ensuring robustness and safety of AI features in the browser.
This internship focuses on frontend development within Opera's R&D team in Wrocław, working on browser-related features and web technologies. The intern will contribute to building and improving user-facing browser interfaces in a hybrid work environment.
