דרושים » תוכנה » Expert Deep Learning Research Engineer - Road Detection

Our CTO Group is looking for an outstanding Physical-AI Applied Researcher to join our team.
The CTO Group is a small, elite research unit shaping the next generation of algorithmic foundations behind our autonomous driving systems. The group operates at the core of the decision-making and planning stack, addressing some of the most challenging problems in real-world autonomy.
We are seeking a researcher who thrives at the intersection of machine learning, decision-making, and algorithmic rigor - someone who is excited about advancing learning-based approaches for safety-critical, large-scale physical systems.
In this role, you will develop novel approaches for planning and decision-making in interactive, multi-agent driving environments. You will combine deep & reinforcement learning with classical algorithmic structure and formal reasoning. The problems are open-ended, scientifically challenging, and deployed at unprecedented scale.
This is a rare opportunity to conduct high-impact applied research, taking ideas from theory and papers into real-world autonomous systems at scale. If youre excited about pushing the boundaries of learning-based decision-making, wed love you to join us and help shape the future of Physical AI.
What will your job look like:
Design and develop novel learning-based algorithms for decision-making and planning in complex physical environments.
Advance model architectures for long-horizon reasoning, multi-agent interaction, and uncertainty-aware prediction.
Integrate deep learning components into structured planning pipelines with clear formal objectives and safety constraints.
Formulate problems mathematically and derive principled learning objectives grounded in real-world system requirements.
Lead research directions from conception to full-scale production.
Develop using Python (PyTorch or similar frameworks) as well as C++/GPU/Cuda.

We are looking for an experienced Deep Learning Algorithm Researcher with a strong focus on Reinforcement Learning to join the CTO Group.
Our CTO Group is a small, elite research and development group responsible for shaping the next generation of algorithmic solutions powering our autonomous driving systems, crowd-sourced HD maps, and advanced driver-assistance technologies.
The role focuses on building a learning-based planning system that has never been deployed at this scale before, leveraging Reinforcement Learning to address complex, interactive driving scenarios. You will work on policy decision making that provides a holistic, system-level view of autonomous behavior, while tackling a deeply challenging technological problem- taking ideas from research to real vehicles, developing algorithms, retraining models, validating results, and seeing the impact on the road within short development cycles.
This is a unique opportunity to take part in early-stage, high-impact projects, develop proof-of-concepts using cutting-edge technologies, and influence our long-term technological direction.
What will your job look like:
Develop and optimize Reinforcement Learning-based planning algorithms, including network architectures, reward design, and training processes.
Apply RL to complex, interactive driving scenarios, complementing classical planning where deterministic approaches fall short.
Work with large-scale simulation environments to enable learning through interaction and diverse policy behaviors.
Prototype algorithms in Python and migrate performance-critical components to efficient C++ / GPU-accelerated implementations.
Take part in fast, iterative development cycles, collaborating closely with the CTO and the team to validate ideas and demonstrate working solutions.

Required Senior Deep Learning Algorithm Developer
Ramat Gan
Full time
A global leader in autonomous vehicle (AV) technology, pioneering advanced driver-assistance systems (ADAS) and self-driving solutions.
Across the company, Senior Deep Learning Algorithm Developers work at the forefront of AV/ADAS innovation - designing, training, and optimizing deep neural networks for tasks such as perception, mapping, and scene understanding. This includes working with large-scale datasets, leveraging frameworks like PyTorch or TensorFlow, and applying state-of-the-art techniques to tackle complex perception and decision-making challenges in real-world driving scenarios.
Senior Deep Learning Algorithm Developers contribute across multiple AI domains, with most opportunities in Computer Vision and additional roles in areas such as NLP/LLMs and 3D Perception (Radar, LiDAR, Fusion). This role serves as a central entry point, enabling us to align your expertise and aspirations with the projects and teams where you can make the greatest impact.
What will your job look like?
Design, develop and implement deep learning algorithms to solve complex problems in computer vision
Take ownership of deep learning projects: Compose product requirements, design solutions, oversee execution, and collaborate with talented Algorithm Developers.
Collaborate with cross-functional teams to understand requirements and develop solutions.
Analyze large datasets to improve algorithm performance and robustness.
Research the latest advancements in deep learning, multi-task learning, AI architectures, and apply them to enhance our algorithms.

Required Senior Deep Learning Researcher
Ramat Gan
Full time
We are a pioneering force in the autonomous vehicles (AV) industry.
Join us to build the brain behind the car - a large-scale, multi-task neural network that powers the core of our autonomous stack.
Youll design and train cutting-edge deep learning models tailored for our custom EyeQ chip, tackling end-to-end challenges and deploying real-world solutions.
From novel architectures and advanced training techniques to performance tuning under tight constraints, youll work closely with software and hardware teams to turn research into high-impact, production-ready systems.
If youre a brilliant, hands-on researcher with a passion for shaping the future - this is your launchpad.
Why us?
Our team is at the forefront of our most advanced AI efforts.
As a central hub for deep learning innovation, were trusted with designing the core neural network architecture that powers the companys flagship products.
If youre seeking a high-impact role among top-tier researchers and developers - this is the place to be.

Required Transformer-Based Deep Learning Algorithm Developer
Ramat Gan
Full time
Join our Perception Solutions team and take part in building a new, impactful project from scratch, shaping the next generation of autonomous driving technology!
Our team is project-oriented, working on significant computer vision challenges and solving them with cutting-edge neural networks combined with heuristic solutions.
In this role, you will join right at the beginning of an end-to-end development cycle. You will leverage advanced approaches, including Transformer-based architectures, to enable direct vision modeling beyond traditional image-processing pipelines.

Our CTO Group is looking for experienced Algorithm Researchers and Developers to join our team!
Which department will you join?
The CTO Group is a small, elite group, whose goal is to build next-generation algorithmic solutions powering our self-driving car, crowd-sourced HD maps, and advanced driver-assistance systems.
The group is primarily focused on the decision-making module of our self-driving car. It leverages a wide range of algorithmic approaches, rigorous formal definitions, and mathematical modeling- enriched by insights drawn from large-scale data and real-world driving experience.
The group is comprised of top-notch developers and researchers and is headed by world-class scientists.
This is a unique opportunity for a passionate technical leader to join the CTO Group, work closely with the CTO on next-generation projects, develop POCs using cutting-edge technologies, shape our technology vision and provide thought leadership to our technical community.
What will your job look like:
Research, design and develop innovative algorithmic solutions.
Mathematical modeling and abstraction of real-life problems.
Code design, implementation, and hands-on development.