Overview In this role you design and evolve a pre-silicon verification framework for a custom ML accelerator, using formal methods and an SMT-based solver to generate realistic assembly tests. You collaborate with verification engineers and hardware teams to shape content and ensure coverage of the design space. You'll advance automation through ML-driven techniques and build APIs to control scheduling and randomness, impacting silicon and software innovation at Annapurna Labs within AWS UC.
Compensation / Benefits- health insurance (medical, dental, vision)
- 401(k) matching
- paid time off
- parML parental leave
- RSUs
- sign-on payments
Responsibilities- Develop understanding of a custom machine learning instruction set architecture
- Model correctness of instruction streams using first order logic
- Create custom APIs to control scheduling and randomness
- Deploy algorithms to ensure concurrent code is safely constructed
- Create coverage metrics to ensure solution space coverage
- Apply machine learning methods to automate content creation
Key requirements- 3+ years building models for business application experience
- PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience
- Experience in patents or publications at top-tier peer-reviewed conferences or journals
- Experience programming in Java, C++, Python or related language
- Experience in algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, high-performance computing
- communication and collaboration with cross-functional teams
- ability to operate under pressure and deliver high-quality results
- problem-solving mindset and curiosity
- SMT-based verification and formal methods
- first-order logic modeling
- API development for scheduling and randomness control
