Deep Learning Software Engineer for Model Quantization

Who we are:
Roofline is building a software development kit to run any model on disruptive hardware at the edge. We are looking for talented and ambitious engineers that are passionate about technology to design and implement new components in our software stack. You will work alongside other world class engineers to enable the full spectrum of AI applications across heterogeneous hardware platforms.

Why us?:
• The opportunity to grow. Be at the forefront of building and shaping an industry-defining venture. There are plenty of opportunities to learn and evolve.
• The team to succeed. We are building the leading AI compiler team in Europe. Join our future-focused team to contribute to meaningful, disruptive innovations with us.
• The flexibility you need. We want you to work in the most productive and sustainable way. Whether you need to take extra time off, adjust your schedule, or have other ideas to maximize your productivity, we’ve got your back.
• The compensation that rewards. We are looking for world class talent and pay accordingly. We offer equity for every employee since we truly want you to participate in our success.
• The culture you desire. We actively make space to build our culture. We organize dedicated regular events and retreats for the whole team.

Your mission:
• Develop edge-AI model quantization flows for different hardware targets
• Interface with existing open-source and close-source quantization frameworks for specific model types or hardware features
• Iterate with customers to design the best quantization flow for our compiler, and help them build the products they dream of
• Partner with a growing open-source community to foster a strong ecosystem around roofline

Your profile:
• Degree in Computer Science/ Electrical Engineering or a related field
• C++ and Python proficiency
• Experience working with Machine Learning frameworks like Pytorch, TensorFlow, Jax.
• Proven understanding of software engineering principles, data structures, design patterns, and algorithms 
• Ambition and curiosity to solve complex problems, a strong mindset to take ownership of your tasks to drive our solutions forwards, and collaborative attitude to foster our culture

Nice to haves: 
• Knowledge and experience in training and deploying quantized deep learning architectures
• Experience with AI model exporting and inference engines like ONNX, ExecuTorch, TFLite 
• Knowledge of AI algorithms, experience with using AI accelerators or compiling to relevant hardware
• Meaningful contributions to open-source communities
• Experience working with embedded targets or compiler infrastructure, e.g., LLVM, MLIR