Senior/Staff Applications Engineer - Embedded AI

Axelera AI

20h • Hybrid

About The Position

The Applications team develops the customer-facing components of Axelera AI’s Voyager SDK, including low-code model deployment, end-to-end pipeline development and application integration and analytics. Customers use these tools to quickly evaluate, prototype and build complete production AI solutions accelerated by Axelera AI devices. The Applications team develops cutting-edge development tools with simple APIs that ensure the solutions deployed by our customers reach the highest levels of performance and accuracy available in the market.
We are seeking skilled and innovative software engineers to help us scale the product to support a wider range of models, pipelines and end-customer use cases. This is a challenging but rewarding role which can cover a variety of tasks such as compiling high-level graphical representations of ML-based pipelines, optimizing memory usage and synchronization on heterogeneous hardware targets and writing low-level implementations of computer vision operators for specialised processing elements.

Requirements

• BS/MS in Computer Science, Electrical Engineering or equivalent work experience in the semiconductor and/or AI industry
• Proven hands-on experience with edge deployment frameworks such as OpenVINO or TensorRT
• Proficiency in AI application development using Python, with extensive experience in ML libraries such as PyTorch and TensorFlow
• Demonstrated ability to build and deploy end-to-end pipelines with quantized models
• Experience in training models using transfer learning to leverage pre-trained models for new tasks
• Strong problem-solving skills and an ability to troubleshoot and debug complex multi-dimensional problems
• Proficient Linux skills
• Practical knowledge of agile development using tools such as Jira, Git and GitHub
• Self-motivated with the ability to thrive in a fast-paced collaborative startup environment

Nice To Haves

• Familiarity with model optimisation techniques such as quantization, compression and pruning a plus
• Experience with MLIR and ONNXRuntime a plus

Responsibilities

• Studying research papers, open-source code repositories and product documentation to deploy new models using the Voyager SDK, and evaluating their performance and accuracy
• Implementing image pre and post processing operators, collaborating with the compiler team to troubleshoot compilation issues, and writing decoders that transform inference tensors to metadata for ease of use by application developers
• Integrating popular industry-standard model frameworks within the SDK to facilitate low-code and no-code deployment of many customer models and datasets
• Defining metadata representations for common types of models (such as bounding boxes and keypoints), creating libraries for evaluating deployed model accuracy on Axelera AI hardware and creating libraries for visually rendering inference results
• Optimizing end-to-end pipeline latency and throughput, root causing any bottlenecks arising on supported hardware platforms, and developing profiling tools to help customers more easily analyse and understand bottlenecks in their own pipelines
• Writing and maintaining comprehensive product documentation and sharing knowledge with team members, promoting best practices and continuous improvement

Benefits

• We offer an attractive compensation package, including a pension plan, extensive employee insurances and the option to get company shares.
• An open culture that supports creativity and continual innovation is awaiting you.
• Collaborative ownership and freedom with responsibility is characteristic for the way we act and work as a team.
• At Axelera AI, we wholeheartedly embrace equal opportunity and hold diversity in the highest regard. Our steadfast commitment is to cultivate a warm and inclusive environment that empowers and celebrates every member of our team. We welcome applicants from all backgrounds to join us in shaping the future of AI.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Number of Employees: 101-250 employees