7 days ago
Sŏngnam, Korea, SouthSenior
Responsibilities
- Develop software and optimize execution environments for efficient AI-model inference on GPU, NPU, and other hardware accelerators.
- Implement encoding and preprocessing for AI-model inputs, including images, and decoding and postprocessing for model outputs.
- Profile AI models and applications in embedded systems and optimize hardware-resource utilization and inference performance.
- Improve applications and software frameworks to support continuous AI-model updates and deployment.
- Help develop performance-validation frameworks to analyze and predict AI-model performance in vehicles.
- Participate in the development of software for embedded autonomous-driving AI systems.
Requirements
- At least 5 years of development experience in embedded software, AI software, computer vision, or a related field.
- A master's degree or higher in software engineering, computer vision, artificial intelligence, machine learning/deep learning, or a related field, or equivalent practical experience.
- Understanding of machine-learning and deep-learning model structures and inference processes.
- Understanding of CPU, GPU, and NPU architectures and experience with low-level performance optimization.
- Proficiency in software development using C/C++ and Shell/Python.
- Experience developing software on Linux or QNX.
- Ability to diagnose and resolve software performance-analysis and optimization problems in embedded systems.
- Preferred: experience analyzing and optimizing machine-learning and deep-learning workloads.
- Preferred: experience optimizing and analyzing linear-algebra routines used in deep-learning computation.
- Preferred: system-level optimization experience with image processing, computer vision, or robotics algorithms.
- Preferred: experience with hardware acceleration and computational optimization using CUDA, MKL, SIMD, or NEON.
- Preferred: experience building inference environments for vehicle AI models or developing embedded AI applications.
- Preferred: experience applying VLA or end-to-end autonomous-driving AI models to vehicles and validating their performance.
Benefits
- A three-month probationary period may apply.
- The interview process may include document screening, a coding test, video and in-person interviews, and compensation and onboarding discussions.
- The interview process and schedule may change depending on circumstances, with results communicated by email.
- Veterans and individuals eligible for employment protection are given preference according to applicable law.
- Registered persons with disabilities are given preference under applicable employment law.
- A reference check may be conducted with the applicant's consent after the interview process.
Categories
About 42dot
42dot builds software-defined vehicle and autonomous mobility platforms for automakers and mobility service providers. Its products include AI-driven vehicle software, data-based update services, and core platform components such as API gateways and identity/access management to connect services securely. The privately held company is headquartered in Seongnam-si, Gyeonggi-do, and focuses on transportation and automotive markets.