Blaize - Senior Software Engineer - Artificial Intelligence/Machine Learning (3-7 yrs)

About the Role :

We are seeking a highly motivated and experienced Senior Software Engineer to join our team and contribute to the development of our high-performance computing platform.

This role will focus on compiler and kernel development for the Blaize hardware, working on optimizing performance, enabling new AI/ML models, and bridging the gap between high-level frameworks and our custom hardware.

This is a fantastic opportunity to work on challenging parallelization problems, contribute to a cutting-edge hardware platform, and directly impact the future of AI/ML acceleration.

Responsibilities :

- Kernel Development : Design, develop, and maintain high-performance kernels for the Blaize hardware, optimizing for speed, power efficiency, and memory utilization.

- Compiler Optimization : Write graph-level compiler passes and optimizations for the Blaize Graph Compiler/Optimizer, improving the performance and efficiency of compiled models.

- Framework Integration : Lower operators from popular AI/ML frameworks like TVM, ONNX, and PyTorch to the hardware level binary, enabling seamless deployment of models on the Blaize platform.

- Parallelization : Tackle complex parallelization problems to maximize the utilization of the Blaize GSP (Graph Stream Processor) and achieve optimal performance for complex operators.

- Testing & Verification : Perform rigorous testing and verification of developed kernels and compiler optimizations to ensure correctness and performance.

- Collaboration & Communication : Collaborate closely with hardware engineers, architects, and other software engineers to design, implement, and integrate software components. Communicate effectively with internal teams and vendors.

- Requirements Analysis : Understand business needs and translate them into technical requirements for software development.

- Software Development Lifecycle : Participate in all stages of the software development lifecycle, from design and implementation to testing and deployment.

- Quality Assurance : Contribute to ensuring the quality of software releases through testing strategies for new features and changes. Develop comprehensive test plans and collaborate with the automation team to ensure proper regression test coverage. Contribute to automation frameworks for the graph optimizer.

- Hardware Bringup : Contribute to hardware bringup efforts and integration of software components with the hardware platform.

Qualifications :

- BTech/MTech in Computer Science or a related field.

- 3-7 years of experience in software development, with at least 3+ years in compiler or kernel development, ideally for GPUs or specialized hardware.

- Strong foundation in computer science fundamentals, including data structures, algorithms, and computer architecture.

- Proficiency in C/C++ and Python.

- Experience with parallel programming and optimization techniques.

- Understanding of graph processing and familiarity with assembly programming.

- Experience with GPU programming and writing parallel kernels is highly desirable.

- Familiarity with AI/ML frameworks (TVM, ONNX, PyTorch) and deep learning models (YOLO, LLMs) is a plus.

- Experience with traditional computer vision algorithms and image processing is preferred.

- Strong analytical and debugging skills.

- Knowledge of test automation tools and regression setup.

- Hardware bringup experience is a plus.

Required Skills :

- Computer Architecture

- Graph Processing

- Assembly Programming

- C/C++

- Python

- Data Structures

- Algorithms

- DNNs (Deep Neural Networks)

- ML Networks

- Parallel Programming

- Problem-Solving Skills

- Analytical Skills

- Debugging Skills

Preferred Skills :

- Computer Vision

- Image Processing

- AI/ML

- Test Automation

- Hardware Bringup

- GPU Programming

- YOLO Networks

- LLMs (Large Language Models)