AI Vision Processors For Edge Applications

Our solutions make cameras smarter by extracting valuable data from high-resolution video streams.

Job Description

We are seeking a Software Engineer to develop and optimize low-level software and microcode for AI workloads on Ambarella AI SoCs. This role focuses on AI workload deployment, performance optimization, heterogeneous compute orchestration, and system-level debugging across the silicon lifecycle.

This is a hands-on engineering role at the hardware–software boundary.

Key Responsibilities:

• Low-Level & Runtime Development
  • Develop deep expertise in Ambarella AI SoC and accelerator architecture.
  • Design, implement, and debug microcode, runtime, and system-level software to deploy AI workloads.
  • Efficiently utilize heterogeneous compute cores and multi-level memory hierarchies to maximize performance.
• Tooling & Infrastructure
  • Develop tools and infrastructure to streamline workload deployment, profiling, debugging, and performance analysis.
  • Enhance SDKs and workflows to simplify model and algorithm deployment to Ambarella AI platforms.
• Cross-Functional & Customer Collaboration
  • Partner with architecture, hardware, compiler, and application teams to deliver production-ready solutions.
  • Support customers in optimizing and integrating their models onto Ambarella SoCs.

Qualifications & Skills:

• Required
  • Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, or equivalent.
  • 5 to 10 years of experience in systems software, embedded software, firmware engineering.
  • Strong C, Python and low-level programming experience.
  • Deep understanding of Computer architecture and Microprocessor fundamentals.
  • Experience with modern software development processes.
  • Strong analytical skills, with a passion for solving complex challenges.
  • Strong communication, interpersonal and planning skills.
• Preferred
  • Experience with heterogenous compute core SoCs and accelerators.
  • Knowledge of Runtimes, Operating Systems and/or RTOS internals.
  • Experience debugging system-level issues across components and layers.
• Nice to have
  • Knowledge of Deep Learning, Computer Vision fundamentals.
  • Knowledge of AI workloads (CNNs, LLMs/VLMs), particularly how they map efficiently to hardware.

What Makes You Successful in This Role

• You enjoy working close to the hardware.
• You are driven by performance optimization challenges.
• You are comfortable navigating ambiguity in fast-moving, product-driven environments.

Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 166,000 USD - 188,000 USD for Level 3, and 188,000 USD - 212,000 USD for Level 4.