Embedded Software Engineer II

Meta Platforms • Sunnyvale, CA

9h • Onsite

About The Position

The Embedded Software Engineer will design and deploy high-performance computer vision and machine learning pipelines on resource-constrained edge hardware. The role focuses on optimizing concurrent machine-learning workloads to maximize throughput and minimize latency when multiple edge-AI features run simultaneously, and integrating edge-AI algorithms with the Android camera framework and multimedia subsystems. The engineer will work across software and hardware teams to connect low-level camera sensor subsystems with on-device neural processing units (NPUs), while profiling and optimizing memory footprint, power consumption, and execution timing to meet on-device performance constraints. The position is onsite three days in Sunnyvale, California, and has a stated duration of 12 months.

Requirements

• Bachelor’s degree in Computer Science, Electrical Engineering, Computer Engineering, or a related technical field, or equivalent practical experience.
• Proficiency in Python and C/C++ for low-level software development and optimization.
• Experience with machine-learning frameworks optimized for edge deployment, such as TensorFlow Lite, ONNX Runtime, or PyTorch Edge.
• Familiarity with the Android platform stack, particularly multimedia or camera subsystem integration.
• Solid understanding of computer vision fundamentals, digital signal processing (DSP), or basic camera architectures.
• Previous AI experience.

Nice To Haves

• Hands-on experience developing within the Android camera framework to control, process, route, and transform real-time image streams.
• Experience with model optimization techniques such as quantization, pruning, and hardware-specific compilation for NPUs, GPUs, or DSPs.
• Background developing low-latency algorithms for real-time edge applications, such as biometric verification, image restoration, or on-device language processing.
• Familiarity with hardware-constrained vision pipelines, including specialized sensor integration and multithreaded concurrency models.
• Hands-on experience debugging low-level software with hardware profiling tools to isolate memory bottlenecks and scheduling conflicts.

Responsibilities

• Design and deploy high-performance computer vision and machine learning pipelines on resource-constrained edge hardware.
• Optimize concurrent machine-learning workloads to maximize throughput and minimize latency when multiple edge-AI features run simultaneously.
• Integrate edge-AI algorithms within the Android camera framework and multimedia subsystems.
• Collaborate with software and hardware teams to bridge low-level camera sensor subsystems with on-device neural processing units (NPUs).
• Profile and optimize memory footprint, power consumption, and execution timing to meet on-device performance constraints.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level