דרושים » תוכנה » Experienced Deep Learning Optimization Engineer- Compilers Team

We are looking for a deep learning software engineer to join the Autonomous Driving software group in Haifa, focusing on Deep Learning optimizations. This role offers an exciting opportunity to collaborate with highly talented engineers, contribute to an innovative product, and work with cutting-edge AI technologies.
What will your job look like:
Develop a software product that optimizes deep learning networks. The optimizations include learnable techniques such as quantization, pruning and compression. This software product is the initial stage of the deep learning inference flow and is essential for enabling our deep learning networks to operate efficiently on low-power hardware within vehicles.
Development is mostly in Python programming language, using deep learning frameworks such as Pytorch.
Collaborate closely with our algorithm teams to ensure the fast and accurate deployment of their state-of-the-art models.
The work encompasses the entire software development cycle, including code implementation, unit testing, CI/CD processes, and more.
Literature research and POC implementation of new optimization algorithms.
Your work will position you at the forefront of machine learning optimizations.

Required Reinforcement Learning Researcher | Learned-Policy Group
About the team:
Build the intelligence behind the next driving decision.
Were building a reinforcement-learning driving planner for complex, interactive road scenarios. Were looking for a researcher to help take it from simulation to real vehicles.
Youll develop policy models, rewards, and training methods. Youll define how driving behavior is evaluated, analyze failures in closed loop, and validate improvements on the road. Youll work in a small team and collaborate with control and other algorithm teams.
This is a high-impact role with direct influence on a core part of our
driving technology and its future products.
What will your job look like?
Research and develop reinforcement-learning planning algorithms, including policy architectures, reward design, training objectives, and optimization methods.
Train and evaluate RL policies for difficult, interactive driving scenarios, building on the existing learning-based planner and complementary classical components.
Develop evaluation methods and relevant metrics for safety, progress, comfort, and interaction quality, and use them to guide experiments and analyze failures.
Build simulation-based training and closed-loop evaluation workflows.
Turn research ideas into reliable components of the driving stack.