EN_3030_Software Engineer (SoC Optimization)

-About the role- This position is intended for software engineers with experience in edge AI inference optimization and deployment optimization. Turing is a deep-tech startup developing multimodal generative AI to achieve fully autonomous driving. In this role, you will work across the boundaries of ML models, compilers, runtimes, and SoC/hardware, taking ownership of enabling stable and high-performance inference in resource-constrained automotive edge environments. Your mission is to identify the optimal balance between performance and cost for production-scale deployment, while ensuring reliability and maintainability, and translate those trade-offs into concrete system performance requirements. Responsibilities 1. Accelerate Inference Performance * Collaborate across ML and systems teams to optimize end-to-end inference performance, from identifying bottlenecks to implementing improvements. * Improve execution efficiency of ML models running on automotive edge devices. 2. Improve the Deployment Pipeline * Automate the entire model deployment workflow, including model conversion, quantization, build, and deployment. * Build and maintain automated build environments and CI pipelines for reliable deployment. 3. Enable New SoC Platforms * Evaluate and bring up next-generation SoCs through exploratory development. * Drive model deployment, implementation, and performance optimization on new hardware platforms.

■Required qualifications Candidates should have experience in at least one of the following machine learning optimization technologies: ・Hands-on experience implementing inference pipelines using SDKs such as NVIDIA TensorRT or similar inference acceleration frameworks. ・Experience analyzing and optimizing machine learning inference bottlenecks using profiling tools such as NVIDIA Nsight. ・Experience implementing custom operators and supporting PyTorch ↔ ONNX model conversion workflows. ・Knowledge of and practical experience with model optimization techniques such as quantization, pruning, or other inference acceleration methods. ・Experience with parallel programming using CUDA or equivalent GPU programming frameworks.

■Preferred qualifications ・Experience developing systems involving sensor fusion, LiDAR, SLAM, computer vision, or camera-based perception. ・Hands-on experience deploying and optimizing software on automotive SoCs, such as NVIDIA DRIVE Orin or similar autonomous driving platforms. ・Professional experience in the autonomous driving and/or robotics domains. ・A proven track record of contributions to open-source software (OSS) projects.

■Who we are looking for ・Driven to build a world-class company ・Self-starter who takes initiative on everything ・Humble, with genuine empathy for others ・Flexible and excited by rapid organizational and business growth ・Growth-oriented mindset ・Resilient — able to find joy even in tough challenges ◆Tech stack ・Language：Python ・Libraries：PyTorch、OpenCV、MMDetection、ONNX ・Middleware：Slurm ・Cloud：AWS、GCP ・Platform：Jetson、Linux 【LEARN MORE】 ▼Company website https://tur.ing/ ▼Turing Tech Blog https://zenn.dev/p/turing_motors ▼Turipo（Owned media / Web Magazine） https://tur.ing/turipo 【Application notes】 · Please submit your resume and work history in PDF format. · Do not include salary information (current or desired) in your application documents or entry form. · Our HR team will discuss compensation separately during the selection process.