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.
• By the first half of 2025, vehicles equipped with SVNet surpassed 4 million units globally, maintaining growth despite economic slowdown and intensifying industry competition.
• In 2025, STRADVISION was ranked 10th in domestic AI competitiveness, following companies such as Samsung, Naver, and LG.
Build and productionize novel-view synthesis (side/rear views) and a semantically consistent BEV/Occupancy-based “Vector-Space/World Model” on top of our MV-Gen2 multi-camera vision stack. You will use front-camera video, LiDAR, and CAN/IMU/GNSS logs to achieve high-fidelity, real-time scene reconstruction, prediction, and synthesis, and ship production-grade models/pipelines that integrate with Path Planning/Control.
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]
The selected candidate will be responsible for designing, developing, and optimizing deep learning models for Generative Vision / BEV & Realistic-Novel-View Synthesis for ADAS/Autonomy.
• Generative Vision / World Model R&D
• Design scene understanding, prediction, and synthesis using BEV/Occupancy/3D representations (generate side/rear camera views with strong texture/geometry consistency).
• Multi-Sensor Fusion
• Fuse front/surround cameras + LiDAR + CAN/IMU/GNSS for a 4D dynamic scene representation, including ego-motion/pose estimation.
• Model Architecture
• Use Transformer/Diffusion/NeRF-variants/Gaussian Splatting/Video Autoencoders to enforce spatio-temporal consistency under geometric constraints.
• Training Pipeline
• Build large-scale training/eval pipelines for in-house driving logs and public datasets (nuScenes/Waymo/Argoverse2, etc.), including self-supervised and weakly supervised learning.
• Real-Time Optimization
• Optimize for CUDA/TensorRT/ONNX and (optionally) TDA4VM/Orin; manage multithreading and latency/memory budgets.
• Quantitative Evaluation
• Track PSNR/SSIM/LPIPS + geometric consistency (Depth/Flow/Epipolar), BEV/Occupancy IoU/mAP, temporal stability, and end-to-end planning impact.
• Production Integration
• Integrate Perception Planning/Simulation (replay/augmentation), automate data generation/augmentation and QA gates.
• Research-to-Production
• Monitor literature, inject domain constraints, and bridge SOTA to production using ablations, KD/distillation, and pragmatic trade-offs.
• Master’s degree with 5+ years of relevant industry experience or Ph.D. with 1+ years (or equivalent), with a total of 5–8+ years of hands-on Deep Learning experience across computer vision, machine learning, or robotics domains.
• Strong programming skills : Python required, with C++/CUDA preferred; able to design systems with careful consideration of performance-memory-latency trade-offs.
• Strong foundation in 3D geometry and multiview perception, including camera intrinsics/extrinsics/distortion modeling, coordinate transformations, PnP and bundle adjustment, depth/optical flow estimation, and BEV/occupancy representations.
• Hands-on experience with Temporal/Transformer/Diffusion (at least 1 stack), including large-scale training and hyperparameter tuning.
• Demonstrated expertise in building large-scale video and multiview training pipelines in PyTorch, including distributed training, mixed precision, checkpointing, logging, and replay mechanisms.
• Experience in driving log data engineering(video-LiDAR-CAN alignment, timestamping and sensor drift handling).
[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.
• By the first half of 2025, vehicles equipped with SVNet surpassed 4 million units globally, maintaining growth despite economic slowdown and intensifying industry competition.
• In 2025, STRADVISION was ranked 10th in domestic AI competitiveness, following companies such as Samsung, Naver, and LG.
주요업무
[Mission of the Role]Build and productionize novel-view synthesis (side/rear views) and a semantically consistent BEV/Occupancy-based “Vector-Space/World Model” on top of our MV-Gen2 multi-camera vision stack. You will use front-camera video, LiDAR, and CAN/IMU/GNSS logs to achieve high-fidelity, real-time scene reconstruction, prediction, and synthesis, and ship production-grade models/pipelines that integrate with Path Planning/Control.
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]
The selected candidate will be responsible for designing, developing, and optimizing deep learning models for Generative Vision / BEV & Realistic-Novel-View Synthesis for ADAS/Autonomy.
• Generative Vision / World Model R&D
• Design scene understanding, prediction, and synthesis using BEV/Occupancy/3D representations (generate side/rear camera views with strong texture/geometry consistency).
• Multi-Sensor Fusion
• Fuse front/surround cameras + LiDAR + CAN/IMU/GNSS for a 4D dynamic scene representation, including ego-motion/pose estimation.
• Model Architecture
• Use Transformer/Diffusion/NeRF-variants/Gaussian Splatting/Video Autoencoders to enforce spatio-temporal consistency under geometric constraints.
• Training Pipeline
• Build large-scale training/eval pipelines for in-house driving logs and public datasets (nuScenes/Waymo/Argoverse2, etc.), including self-supervised and weakly supervised learning.
• Real-Time Optimization
• Optimize for CUDA/TensorRT/ONNX and (optionally) TDA4VM/Orin; manage multithreading and latency/memory budgets.
• Quantitative Evaluation
• Track PSNR/SSIM/LPIPS + geometric consistency (Depth/Flow/Epipolar), BEV/Occupancy IoU/mAP, temporal stability, and end-to-end planning impact.
• Production Integration
• Integrate Perception Planning/Simulation (replay/augmentation), automate data generation/augmentation and QA gates.
• Research-to-Production
• Monitor literature, inject domain constraints, and bridge SOTA to production using ablations, KD/distillation, and pragmatic trade-offs.
자격요건
[Basic Qualifications]• Master’s degree with 5+ years of relevant industry experience or Ph.D. with 1+ years (or equivalent), with a total of 5–8+ years of hands-on Deep Learning experience across computer vision, machine learning, or robotics domains.
• Strong programming skills : Python required, with C++/CUDA preferred; able to design systems with careful consideration of performance-memory-latency trade-offs.
• Strong foundation in 3D geometry and multiview perception, including camera intrinsics/extrinsics/distortion modeling, coordinate transformations, PnP and bundle adjustment, depth/optical flow estimation, and BEV/occupancy representations.
• Hands-on experience with Temporal/Transformer/Diffusion (at least 1 stack), including large-scale training and hyperparameter tuning.
• Demonstrated expertise in building large-scale video and multiview training pipelines in PyTorch, including distributed training, mixed precision, checkpointing, logging, and replay mechanisms.
• Experience in driving log data engineering(video-LiDAR-CAN alignment, timestamping and sensor drift handling).
