Staff/Principal Software Engineer – AI Applications

Role overview This Staff/Principal-level position leads a major technical area within an AI applications and SDK team that builds customer-facing tools for deploying, prototyping, and scaling machine learning pipelines on specialised edge hardware. The engineer will operate with substantial autonomy, setting architecture and technical direction while partnering closely with product, compiler, and commercial stakeholders to shape the roadmap.

Responsibilities - Own end-to-end technical strategy for a significant portion of the SDK's application layer, translating research, open-source work, and product needs into a coherent roadmap for model deployment, pipeline development, and application integration. - Define reusable architectures for image pre- and post-processing operators and decoders, and partner with compiler engineers to resolve the most difficult compilation challenges. - Drive integration of industry-standard model frameworks into the SDK, building the libraries and architecture that enable low-code and no-code deployment of models and datasets for internal and customer use. - Define metadata representations for common model outputs (e.g., bounding boxes, keypoints) and own the libraries used to evaluate deployed model accuracy and visually render inference results on the target hardware. - Take accountability for end-to-end pipeline latency and throughput across supported platforms, root-causing hard bottlenecks and building profiling tools that raise the team's performance diagnostics bar. - Represent the team's technical capabilities to business stakeholders, mentor engineers, and drive documentation standards and best practices.

Requirements - BS/MS in Computer Science, Electrical Engineering, or equivalent, with typically 8+ years of hands-on experience in the semiconductor and/or AI industry. - Deep expertise with edge deployment frameworks such as OpenVINO or TensorRT, and experience with GPU computing APIs such as OpenCL and Vulkan. - Strong track record of model optimisation techniques including quantization, compression, and pruning. - Expert-level proficiency in Python and C++ for AI applications, with extensive experience using ML libraries such as PyTorch and TensorFlow. - Demonstrated ability to architect, build, and deploy end-to-end pipelines with quantized models at scale, and to create reusable frameworks. - Proven ability to navigate deep ambiguity, exercise strong technical judgement under pressure, and deliver outcomes without clear playbooks; experience mentoring engineers and engaging with senior technical and business stakeholders.

Nice to have - Experience with MLIR and ONNXRuntime. - Experience training models via transfer learning to adapt pre-trained models to new tasks. - Proficient Linux skills and practical knowledge of agile development with tools such as Jira, Git, and GitHub.

Benefits and work setup Flexible work arrangements are supported, including office-based, fully remote within Europe, or relocation options, with priority given to candidates based in or open to Bavaria (Germany), Belgium, or Italy. The package includes an attractive compensation plan with pension, extensive employee insurances, and an option to receive company shares. The culture emphasises open collaboration, creative ownership, and an inclusive environment that welcomes applicants from all backgrounds.