Senior Embedded AI Researcher

Senior Embedded AI Researcher

Join Nexar Inc. to work at the intersection of AI research and embedded systems.

We are looking for a highly skilled engineer to bring our cutting‑edge computer vision models to life on Ambarella CVxx‑based dash cams, working closely with research engineers to optimize neural networks for object detection, video reconstruction, and collision prediction in a resource‑constrained embedded environment.

• Meaningful impact on roads and city safety
• Flexible schedule, work location, and benefits
• Competitive compensation
• Fast‑paced environment with smart, driven colleagues
• Professional and personal growth opportunities
• Team‑building events and well‑being initiatives

Nexar turns cars into vision sensors to understand the world. Our platform powers vision‑connected services and apps at scale, driving autonomous vehicle and public sector projects worldwide.

• BS/MS/PhD in Computer Science, Electrical Engineering, or related field
• 3+ years of industry experience in embedded ML, edge AI, or related domains
• Track record of shipping ML models in production embedded systems
• Proficiency in C/C++ for embedded systems and performance‑critical code
• Understanding of computer architecture: cache hierarchies, memory systems, SIMD/vector processing
• Knowledge of DMA, interrupts, and hardware‑software interfaces
• Experience with embedded AI platforms and hardware accelerators (e.g., Ambarella CVFlow, NVIDIA Jetson, Qualcomm Hexagon)
• Deep understanding of computer architecture, kernel scheduling, I/O, memory management, GPU/NPU pipelines
• Experience with heterogeneous computing (CPU/GPU/NPU/DSP coordination)
• Prior experience deploying neural networks to resource‑constrained devices (mobile, automotive, IoT)
• Professional experience with Tensor Flow, PyTorch, or Caffe

• Direct experience with Ambarella SoCs and CVFlow architecture
• Background in computer vision applications (object detection, segmentation, tracking)
• Experience with automotive ADAS development and safety standards
• Knowledge of video codec integration (H.264/H.265)
• Understanding of fixed‑point arithmetic and numerical stability
• Experience with Tensor
  
  RT, LiteRT, ONNX Runtime, or similar inference engines
• Contributions to ML deployment frameworks or tool chains

• Develop, optimize, and deploy deep learning models on Ambarella CVFlow‑based camera platforms
• Translate state‑of‑the‑art AI models into production‑ready code, bridging research and systems teams
• Deep‑dive into CVFlow architecture to maximize neural network performance
• Profile model performance and address bottlenecks in I/O, memory, and compute
• Implement model optimisation techniques: quantization, pruning, knowledge distillation, architecture search to meet latency and power budgets while maintaining accuracy targets
• Develop custom operators and layers optimized for CVFlow’s vision processing engine
• Collaborate with systems engineers to integrate AI models with camera firmware and software
• Stay current with advances in embedded AI, GenAI, and computer vision

• Excited about squeezing performance gains from carefully tuned operators
• Can explain both Res Net architecture and L2 cache eviction policies
• Think about problems both from model‑architectural and resource‑constraint perspectives
• Enjoy the intersection of research innovation and engineering pragmatism
• Motivated by the constraints of real‑time, power‑limited embedded systems