
Staff/Principal Software Engineer – AI Applications
Posted 1 day ago

Posted 1 day ago
This is a fully remote position, open to applicants in Netherlands.
• Take charge of the comprehensive technical strategy for a significant component of the Voyager SDK application layer.
• Convert research papers, open-source projects, and product specifications into a strategic plan for model deployment, pipeline development, and application integration.
• Establish the technical direction for image pre/post-processing operators and decoders.
• Develop reusable architectures and collaborate with the compiler team on complex compilation challenges.
• Lead the integration of industry-standard model frameworks into the SDK.
• Specify reusable libraries and architecture for low-code and no-code model and dataset deployment.
• Define company-wide metadata standards for model types, including bounding boxes and keypoints.
• Manage libraries for assessing deployed model accuracy and visually rendering inference results on Axelera AI hardware.
• Be accountable for pipeline latency and throughput across various supported hardware platforms.
• Identify bottlenecks and create profiling tools and frameworks to diagnose performance issues.
• Represent the Applications team’s technical capabilities to business stakeholders, clients, and the industry.
• Mentor and cultivate the skills of engineers.
• Promote documentation standards and best practices throughout the team.
• Help define the Applications team’s technical roadmap in collaboration with commercial and product stakeholders.
• BS/MS in Computer Science, Electrical Engineering, or a related field.
• Typically over 8 years of hands-on experience in the semiconductor and/or AI sectors.
• In-depth, hands-on knowledge of edge deployment frameworks like OpenVINO or TensorRT.
• Familiarity with GPU computing APIs such as OpenCL and Vulkan.
• Proven experience in applying quantization, compression, and pruning techniques.
• Expert-level AI application development skills using Python.
• Extensive experience with machine learning libraries such as PyTorch and TensorFlow.
• Advanced proficiency in both Python and C++.
• Capability to architect, build, and deploy end-to-end pipelines utilizing quantized models at scale.
• Experience in creating reusable frameworks.
• Background in training models using transfer learning.
• Familiarity with MLIR and ONNXRuntime is a plus.
• Strong technical judgment under pressure when facing complex, multi-dimensional problems.
• Excellent communication and influencing abilities.
• Proven experience handling high-stakes discussions with senior technical and business stakeholders.
• Experience in representing technical work to customers or industry stakeholders.
• Experience in mentoring and developing junior engineers.
• Proficient in Linux.
• Practical understanding of agile development practices using Jira, Git, and GitHub.
• Self-driven and capable of establishing technical direction with considerable autonomy.
• Ability to succeed in a fast-paced, collaborative startup culture.
• Pension plan.
• Comprehensive employee insurance options.
• Opportunity to acquire company shares.
• Flexible working arrangements.
• Remote work from any European country, including the UK.
• Relocation assistance to Italy or the Netherlands.
• Open culture that encourages creativity and ongoing innovation.
• Collaborative ownership and freedom accompanied by responsibility.
• Equal-opportunity and inclusive work environment.
Alzheimer's Association®
Capital One
Capital One
Get handpicked remote jobs straight to your inbox weekly.