We are looking for an AI & Application Engineer / Technical Lead to develop, validate, integrate, and optimize AI models and application-layer logic for embedded camera and edge AI platforms. The role is responsible for ensuring that AI workloads, inference pipelines, and application functions operate reliably on both reference prototype platforms and custom hardware.

Key Responsibilities

• Develop, train, fine-tune, and validate AI models based on product and use-case requirements.
• Optimize AI models for edge deployment considering accuracy, latency, FPS, memory, compute load, and accelerator usage.
• Validate model performance using lab and real-world datasets across day, night, low-light, IR, motion blur, WDR/HDR, and field conditions.
• Define model acceptance criteria including accuracy, precision, recall, false positives/negatives, latency, throughput, and stability.
• Develop inference logic, post-processing, event generation, alert logic, metadata generation, and application workflows.
• Implement video stream handling, AI pipeline execution, evidence generation, storage, networking, and system integration functions.
• Provide early hardware inputs for compute, memory, accelerator, storage, networking, camera streams, resolution, FPS, and runtime needs.
• Support hardware architecture decisions including SoC/GPU/NPU, RAM, storage, interfaces, thermal design, and workload profiles.
• Validate AI/application operation on reference prototype platforms and revalidate the same stack on final custom hardware.
• Benchmark FPS, latency, CPU/GPU/NPU usage, memory, thermals, storage, and network bandwidth; compare prototype and custom hardware results.
• Provide integration feedback, identify bottlenecks, own AI/application defects, and support root-cause analysis through closure.
• Optimize AI/application pipelines for real-time, multi-camera, high-resolution, high-FPS, low-latency, and stable 24/7 operation.