Software Engineer II — AI Compiler Engineer

Job Title

Software Engineer II — AI Compiler Engineer

Role Summary

Develop and optimize a deep learning/AI graph compiler that converts neural network models from frameworks (PyTorch, TensorFlow, etc.) into high-performance code for embedded processors, DSPs, and specialized accelerators. Work on compiler front- and back-end components, runtime integration, and hardware-aware optimizations as part of an IP/SoC tools team.

Experience Level

Mid-level. Typically requires 3–5+ years of relevant software and compiler development experience.

Responsibilities

Primary engineering responsibilities for this role include building compiler components, runtime integration, and performance validation:

• Design and implement compiler passes and IR lowering using modern compiler frameworks (e.g., LLVM, MLIR).
• Implement and optimize neural-network operations and code generation for embedded processors and accelerators.
• Develop optimization techniques to map CNNs/RNNs efficiently to Xtensa processors, DSPs, and specialized hardware.
• Integrate optimized kernels into a runtime and validate end-to-end NN execution and performance.
• Benchmark and profile networks on target embedded and accelerator platforms; iterate on optimizations.
• Collaborate with hardware designers to identify opportunities for hardware acceleration and co-design.
• Design multiprocessor/multicore partitioning and scheduling strategies for target platforms.
• Write validation programs and tests to ensure correctness and performance of the compiler toolchain.

Requirements

Must-have technical skills and experience:

• Strong C and C++ programming skills with 3–5+ years of practical experience.
• Experience developing software on Linux and Windows, including testing, debugging, and release processes.
• Practical experience with compiler toolchains and technologies such as LLVM and MLIR.
• Experience implementing compilation techniques (loop optimizations, IR construction/transition/lowering, polyhedral models).

Nice-to-have:

• Production compiler development experience (3+ years preferred).
• Python programming experience.
• Experience with CNNs and deep learning frameworks (TensorFlow, PyTorch, Caffe) and ONNX or other exchange formats.
• Familiarity with deep learning compilation projects (Glow, TVM, XLA) and common network types (classification, detection, segmentation, RNNs).
• Experience optimizing code for embedded platforms and DSPs (including DMA engines).

Education Requirements

Bachelor's degree in Computer Science or Computer Engineering is expected, or equivalent practical experience. Master's or PhD in a related field is listed as a plus.

About the Company

Company: Cadence Design Systems

Headquarters: San Jose, California, USA

Cadence Design Systems is a global electronic design automation company that provides software, hardware, and intellectual property for designing advanced semiconductor chips. With over 25 years in the industry, Cadence is known for its innovative technology solutions and has been recognized by Fortune Magazine as one of the 100 Best Companies to Work For. The company is dedicated to solving complex technical challenges in order to enable customers to create revolutionary products and experiences.