注册一亩三分地论坛,查看更多干货!
您需要 登录 才可以下载或查看附件。没有帐号?注册账号 
x
【认识公司】
黑芝麻智能科技有限公司https://bst.ai/ 成立于2016年,是行业领先的车规级自动驾驶计算芯片和平台研发企业,专注于高算力芯片及平台技术的研发。公司提供完整的自动驾驶和车路协同解决方案,涵盖车规级设计、学习型图像处理、低功耗精准感知等自动驾驶感知计算芯片和平台,推动自动驾驶产业链相关产品的快速落地。
黑芝麻智能在全球拥有超过1200名员工,其中硅谷办公室有80多人。核心团队成员来自博世、OV、英伟达、安霸、微软、高通、华为和中兴等行业顶尖公司,平均具备15年以上行业经验。团队实力雄厚,芯片流片成功率达到100%,人员发展稳定,且公司已在香港上市。
【工作地点】
San Jose/Singapore
对自动驾驶行业和AI 芯片感兴趣的朋友可以发送到HR邮箱: yuefeng.xue@bst.ai
【Openings】
ASIC Design Engineer(new grad友好)
Job description:
In this role, you will be helping us define the u-arch, finish RTL design and verification for a ground-breaking AI inference accelerator. You will also work closely with our algorithm, compiler, and architecture teams to perform tasks like RTL performance modeling and design space exploration.
Responsibilities:
• Develop micro-architecture for Neural Network Processor (NPU) related designs.
• RTL design using Verilog/System Verilog coding and HLS tools (Catapult).
• Measure and analyze metrics (power, performance, area) to meet key objectives & results.
• Work closely with architects, and verifiers to drive verification signoff in an efficient manner.
• Support FPGA tasks such as emulation, validation and debugging.
Qualifications:
• Master’s degree and above in Electrical/Electronics/Computer Engineering.
• Fluent with HDL languages (Verilog, SystemVerilog), Familiar with scripting languages like Python, Perl, or C/C++ .
• Familiar with all phases of ASIC frontend and sign-off design, Familiar with relevant EDA tools and CAD flow.
• Prior design experience in image/vision/video data processing, algorithm acceleration, processor (CPU/GPU/DSP/NPU) is a plus.
• Good communication skills, teamwork and motivation to take on new challenges.
Software Engineer, AI Compiler (new grad友好, C++熟悉)
Job description:
We are looking for an experienced AI/ML engineer passionate about deploying AI inference and end to end enablement, AI framework integration, model accuracy, and performance analysis and tuning. You might be an ideal candidate if you are seeking to develop high quality, innovative, and scalable software that enables state of the art AI inference models to run efficiently and accurately on the BST Intelligence processors.
Responsibilities:
• Contributing to deep learning infrastructure, data pipelines, tools and workflows that lay the foundation for building AI at scale.
• Writing software to deploy AI models and pipelines in real time applications (inference).
• Apply low precision inference, quantization, and compression of DNNs.
• Continuously improve inference latency, accuracy and power consumption of DNNs.
• Stay up to date with the latest research and innovations in deep learning, implement and experiment with new ideas
Qualifications:
• You are graduating with a MS, or Ph.D. degree in Computer Science, Computer Engineering, Applied Math, or related field.
• You can work independently, define project goals and scope, and lead your own development effort.
• Strong C++/ C or Python programming and software design skills, including debugging, performance analysis, and test design.
• Strong expertise on one of these directions:
– deep learning quantization
– NN compiler (TVM, MLIR, GLOW, LLVM) experience
– NN model pruning
– Cadence DSP programming
Ways to stand out from the crowd:
• Numerical methods experience
• Knowledge of computer architecture
• Python experience
• Experience with Deep Learning Frameworks such as TensorFlow, PyTorch, and MXNet
AI Perception Algorithm Engineer/ Scientist
Job description:
Our deep learning team drives the perception capabilities that enable autonomous vehicles to understand and interact with the world. We’re seeking a motivated research scientist to develop advanced algorithms and deep learning solutions for autonomous driving and ADAS applications, leveraging both camera and lidar data. Your work will directly contribute to novel perception systems and enable real-time, hardware-optimized performance on embedded platforms.
Responsibilities:
• Develop deep learning-based perception algorithms, including object detection, lane detection, semantic segmentation, depth estimation, curb detection, etc.
• Design and evaluate cutting-edge network structures and training methods for vision tasks.
• Implement network compression and quantization-aware training to optimize models for ASIC hardware deployment.
• Conduct prototype development, regression testing, benchmark testing, and performance evaluation.
• Prepare demos to showcase model performance and deploy solutions on embedded platforms.
• Conduct R&D, stay updated with the latest research, and propose innovative ideas.
• Contribute to patent applications and publish research papers.
Qualifications:
• MS/PhD in Computer Science, Electrical Engineering, or a related field.
• 2+ years of experience in computer vision, machine learning, and deep learning development.
• Proficiency in Python and C++ with hands-on programming skills; familiarity with embedded systems is a plus.
• Experience with one or more of the following areas:
• Deep network development (visual data focus), object detection, tracking, and 3D computer vision (stereo, optical flow, depth estimation).
• Structure from motion, network-based sensor fusion, and mathematical optimization.
• Familiarity with ADAS and autonomous driving technology, particularly in 3D object detection and semantic segmentation.
• Mandarin proficiency is a plus.
Sr. Embedded Software Engineer
Job description:
In this role, you will develop and debug software for Bird's Eye View (BEV) algorithms, lead the design of the BEV architecture, and refine the existing codebase. You will also collaborate closely with both the algorithm and architecture teams to address software issues and optimize solutions to overcome hardware limitations.
Responsibilities:
• Lead the design, development, integration, and debugging of AD/ADAS embedded software systems.
• Architect software solutions using industry best practices in autonomous technology.
• Implement AI-based perception algorithms on our proprietary hardware platform.
• Adapt algorithms for deployment on various platforms and assess porting outcomes.
• Deliver efficient, high-quality software that meets production standards and functional safety (FuSa) requirements.
• Collaborate closely with customer teams to ensure seamless deployment on target hardware.
• Provide expert guidance on verification and validation strategies to uphold system quality for autonomous platforms.
Qualifications:
• Master's or Bachelor's degree in Software Engineering, Computer Science, Electrical Engineering, Computer Engineering, or related fields from an accredited institution. Master's degree is preferred.
• Minimum of 3 years of hands-on experience in embedded real-time software development, with a demonstrated track record of owning complex designs and implementations.
• Proficiency in C/C++, Python, and scripting languages essential for software development.
• Experience in optimizing algorithms for resource-constrained systems.
• Familiarity with at least one of the following: ARM, DSP, OpenCV, OpenCL, OpenMP, CUDA, and Neon.
• Knowledge of Computer Vision and Deep Learning algorithms is advantageous.
• Strong communication, documentation, and teamwork skills to effectively collaborate in a dynamic environment. |