포지션 상세
This position is with STRADVISION Seoul Office
[About STRADVISION]
We Empower Everything To Perceive Intelligently
With a mission statement of “We Empower Everything To Perceive Intelligently”, STRADVISION is putting all of our effort to make better life for everyone through AI-based camera perception technology. Everyday, we focus on creating AI-based vision perception techonolgy with more than 300 members across 8 offices worldwide and we expect our software to perceive everything precisely & intelligently to make 1% difference in people’s lives. Thus, we are looking for members who would like to join our meaningful journey and face challenges that no one has done it before together at STRADVISION.
[Our Story]
• STRADVISION Seoul Office : https://buly.kr/Edu2Jdr
• STRADVISION’s Core Technology : https://buly.kr/74XS8bi
• STRADVISION's Welfare : https://buly.kr/BpFucdd
[Our Technology]
STRADVISION's Technology : https://stradvision.com/_ENG/dh/technology
• STRADVISION is the FIRST deep-learning based technology start-up company in the world who has obtained ASPICE CL2 certification in 2019.
• STRADVISION has also been honored with the AutoSens Awards for ‘Best-in-Class Software for Perception Systems’(Gold Award Winner) for 2 years in a row(2021, 2022).
• STRADVISION’s outstanding technology was recognized worldwide by successfully completing the Series C funding at KRW 107.6 billion with Aptiv and ZF Group in August, 2022.
• About 167 patents related to autonomous driving/ADAS have been acquired in Korea, Japan, US and Europe. As of today, STRADVISION is actively developing our technology to be differentiated.
The Role as "Guardian of Physical Reality"
In an organization introducing E2E models, the Senior Control Engineer's role evolves beyond a simple path tracker to become the ultimate "Guardian of Physical Reality." They are the last line of defense against the unpredictable outputs of a learning-based system. While an E2E model may learn to map sensor inputs directly to control commands like steering angle 2, this learned mapping does not inherently guarantee stability, smoothness, or adherence to the vehicle's physical limits (e.g., max steering rate, tire friction limits). The Senior Control Engineer's most critical, forward-looking task is therefore to build a safety cage around the E2E model. This is a sophisticated "guardian" system that might take the E2E model's intended behavior as a soft constraint or goal, but which enforces hard constraints based on a trusted vehicle dynamics model. It ensures that even if the AI has a "crazy idea," the vehicle either executes it safely or reverts to a safe state. This role requires a deep, principled understanding of control theory and physics to provide checks and balances for a powerful but potentially volatile large neural network.
The Opportunity: Mastering the Physics of Motion
This role is the critical link between the digital plan and the physical world. You will be responsible for translating the planner's intent into flawless, stable, and comfortable vehicle motion. You will own the vehicle's dynamic soul, ensuring that every maneuver—whether calculated by a classical planner or generated by a neural network—is executed with the utmost precision and safety.
This role is a unique opportunity to work on high-impact, cutting-edge research that directly contributes to the development of next-generation autonomous driving systems.
[Key Responsibilities]
• Modular Stack (The Foundation)
• Design, implement, and tune high-performance longitudinal and lateral vehicle controllers, with an emphasis on Model Predictive Control (MPC) for its strength in handling complex constraints and previewing the planned path.
• Develop high-fidelity vehicle dynamics models for use in simulation and control logic design, and continuously improve model accuracy and perform system identification using deep learning based on real-world driving data.
• Apply data-driven deep learning techniques to develop adaptive control logic that dynamically tunes control parameters in response to real-time changing driving conditions (e.g., road surface, tire wear), thereby increasing robustness.
• Design and implement state estimators (e.g., Extended/Unscented Kalman Filters) to estimate key vehicle states that cannot be directly measured (e.g., velocity, slip angle, road grade).
• Work hands-on with vehicle hardware, interfacing with ECUs, sensors, and actuators via CAN/Ethernet, and lead in-vehicle tuning and validation efforts.
• End-to-End Stack (The Frontier)
• Ensure the stability and physical realism of control outputs generated directly by E2E models. This may involve designing post-processing filters, in-network stability-enhancing layers, or rate limiters.
• Research and develop a "Guardian" controller: a safety-first underlying control system that monitors the E2E policy's commands and intervenes to prevent violations of safety or comfort boundaries.
• Collaborate with the E2E team to incorporate vehicle dynamics constraints directly into the learning process, either by using differentiable physics models or by shaping the policy's action space.
• Define metrics for "control quality" (e.g., ride comfort, smoothness, tracking accuracy) and use them to evaluate and provide feedback on the performance of different E2E policy versions.
• Collaboration
• Collaborate with cross-functional teams, including machine learning engineers, software integration engineers, hardware platform engineers, and quality assurance, to integrate multi-vision E2E algorithms into ADAS systems.
• Participate in code reviews and knowledge-sharing sessions to foster a collaborative work environment.
• Mentoring and Technical Guidance
• Mentor and provide technical guidance to junior/entry engineers.
• Master's or Ph.D. in Mechanical, Electrical, Aerospace Engineering, Robotics, or a related field.
• 7+ years of experience designing dynamic system controllers in the automotive, robotics, or aerospace industries.
• Deep expertise in modern control theory (state-space, LQR, MPC) and classical control (PID).
• High proficiency in MATLAB/Simulink for model-based design and expert-level C++ ability for embedded implementation.
• Solid understanding of vehicle dynamics and modeling.
[About STRADVISION]
We Empower Everything To Perceive Intelligently
With a mission statement of “We Empower Everything To Perceive Intelligently”, STRADVISION is putting all of our effort to make better life for everyone through AI-based camera perception technology. Everyday, we focus on creating AI-based vision perception techonolgy with more than 300 members across 8 offices worldwide and we expect our software to perceive everything precisely & intelligently to make 1% difference in people’s lives. Thus, we are looking for members who would like to join our meaningful journey and face challenges that no one has done it before together at STRADVISION.
[Our Story]
• STRADVISION Seoul Office : https://buly.kr/Edu2Jdr
• STRADVISION’s Core Technology : https://buly.kr/74XS8bi
• STRADVISION's Welfare : https://buly.kr/BpFucdd
[Our Technology]
STRADVISION's Technology : https://stradvision.com/_ENG/dh/technology
• STRADVISION is the FIRST deep-learning based technology start-up company in the world who has obtained ASPICE CL2 certification in 2019.
• STRADVISION has also been honored with the AutoSens Awards for ‘Best-in-Class Software for Perception Systems’(Gold Award Winner) for 2 years in a row(2021, 2022).
• STRADVISION’s outstanding technology was recognized worldwide by successfully completing the Series C funding at KRW 107.6 billion with Aptiv and ZF Group in August, 2022.
• About 167 patents related to autonomous driving/ADAS have been acquired in Korea, Japan, US and Europe. As of today, STRADVISION is actively developing our technology to be differentiated.
주요업무
[Mission of the Role]The Role as "Guardian of Physical Reality"
In an organization introducing E2E models, the Senior Control Engineer's role evolves beyond a simple path tracker to become the ultimate "Guardian of Physical Reality." They are the last line of defense against the unpredictable outputs of a learning-based system. While an E2E model may learn to map sensor inputs directly to control commands like steering angle 2, this learned mapping does not inherently guarantee stability, smoothness, or adherence to the vehicle's physical limits (e.g., max steering rate, tire friction limits). The Senior Control Engineer's most critical, forward-looking task is therefore to build a safety cage around the E2E model. This is a sophisticated "guardian" system that might take the E2E model's intended behavior as a soft constraint or goal, but which enforces hard constraints based on a trusted vehicle dynamics model. It ensures that even if the AI has a "crazy idea," the vehicle either executes it safely or reverts to a safe state. This role requires a deep, principled understanding of control theory and physics to provide checks and balances for a powerful but potentially volatile large neural network.
The Opportunity: Mastering the Physics of Motion
This role is the critical link between the digital plan and the physical world. You will be responsible for translating the planner's intent into flawless, stable, and comfortable vehicle motion. You will own the vehicle's dynamic soul, ensuring that every maneuver—whether calculated by a classical planner or generated by a neural network—is executed with the utmost precision and safety.
This role is a unique opportunity to work on high-impact, cutting-edge research that directly contributes to the development of next-generation autonomous driving systems.
[Key Responsibilities]
• Modular Stack (The Foundation)
• Design, implement, and tune high-performance longitudinal and lateral vehicle controllers, with an emphasis on Model Predictive Control (MPC) for its strength in handling complex constraints and previewing the planned path.
• Develop high-fidelity vehicle dynamics models for use in simulation and control logic design, and continuously improve model accuracy and perform system identification using deep learning based on real-world driving data.
• Apply data-driven deep learning techniques to develop adaptive control logic that dynamically tunes control parameters in response to real-time changing driving conditions (e.g., road surface, tire wear), thereby increasing robustness.
• Design and implement state estimators (e.g., Extended/Unscented Kalman Filters) to estimate key vehicle states that cannot be directly measured (e.g., velocity, slip angle, road grade).
• Work hands-on with vehicle hardware, interfacing with ECUs, sensors, and actuators via CAN/Ethernet, and lead in-vehicle tuning and validation efforts.
• End-to-End Stack (The Frontier)
• Ensure the stability and physical realism of control outputs generated directly by E2E models. This may involve designing post-processing filters, in-network stability-enhancing layers, or rate limiters.
• Research and develop a "Guardian" controller: a safety-first underlying control system that monitors the E2E policy's commands and intervenes to prevent violations of safety or comfort boundaries.
• Collaborate with the E2E team to incorporate vehicle dynamics constraints directly into the learning process, either by using differentiable physics models or by shaping the policy's action space.
• Define metrics for "control quality" (e.g., ride comfort, smoothness, tracking accuracy) and use them to evaluate and provide feedback on the performance of different E2E policy versions.
• Collaboration
• Collaborate with cross-functional teams, including machine learning engineers, software integration engineers, hardware platform engineers, and quality assurance, to integrate multi-vision E2E algorithms into ADAS systems.
• Participate in code reviews and knowledge-sharing sessions to foster a collaborative work environment.
• Mentoring and Technical Guidance
• Mentor and provide technical guidance to junior/entry engineers.
자격요건
[Basic Qualifications]• Master's or Ph.D. in Mechanical, Electrical, Aerospace Engineering, Robotics, or a related field.
• 7+ years of experience designing dynamic system controllers in the automotive, robotics, or aerospace industries.
• Deep expertise in modern control theory (state-space, LQR, MPC) and classical control (PID).
• High proficiency in MATLAB/Simulink for model-based design and expert-level C++ ability for embedded implementation.
• Solid understanding of vehicle dynamics and modeling.
