Description
Location: SF Bay Area (Preferred) or Remote
Join a small, ambitious team revolutionizing embedded AI at Femtosense! We’re delivering state-of-the-art deep learning solutions on our innovative Sparse Processing Unit (SPU) platform, pushing the limits of performance and efficiency. As a leading startup in embedded AI, we’re redefining what’s possible in a wide variety of everyday devices like earbuds, cameras, vehicles, and beyond.
About the Role
As a Deep Learning Compiler Engineer, you’ll play a pivotal role in converting deep learning inference graphs into highly optimized assembly code for our family of novel AI accelerators.
In this role, you will:
- Develop and optimize compiler passes, including graph partitioning, memory allocation, and other critical performance enhancements.
- Work at the intersection of software and hardware to ensure seamless translation of deep learning models into efficient, low-level code in a custom ISA.
- Collaborate closely with the hardware and algorithm teams to support unique features and capabilities of our AI accelerators.
- Design and implement custom MLIR dialects tailored for our Sparse Processing Unit (SPU).
- Explore advanced optimization techniques for complex scheduling and resource allocation problems.
This role offers a rare opportunity to influence the development of a cutting-edge AI stack, from high-level model representation to low-level hardware execution.
Requirements:
- Strong experience in C++ and Python development, with a focus on compiler or systems programming.
- Solid understanding of compiler design, optimization passes, and low-level hardware constraints.
- Familiarity with Mixed-Integer Linear Programming is a plus.
- Hands-on experience with MLIR or other intermediate representations (e.g., TVM or LLVM) is a plus.
- BS, MS, or PhD in Computer Science, Electrical Engineering, or a related field — or equivalent work experience.
- 2+ years of experience or equivalent experience in a related PhD or MS program.
Why Join Us?
- Define how deep learning models run on the next generation of AI accelerators.
- Be part of a tight-knit team with a shared vision for pushing the boundaries of efficiency.
- Make a tangible impact across a broad range of industries and applications.
Femtosense is an equal opportunity employer committed to a diverse workforce which strives to create an inclusive working environment empowering everyone to do their best work. We do not discriminate on the basis of race, ethnicity, religion, gender, gender identity, sexual orientation, age, marital status, veteran status, or disability status.
