Staff Engineer, Compiler
About The Position
The AGI (Artificial General Intelligence) Computing Lab develops scalable platforms to address the computational and memory demands of future AI/ML workloads while minimizing energy consumption and maximizing performance. The team works closely with hardware and software engineers to address workload-specific challenges, explore computing abstractions, and research emerging technologies across memory, computing, interconnect, and AI/ML. The Staff Engineer, Compiler will lead the architecture, design, and implementation of ML compilers for high-performance deep learning applications targeting next-generation AGI hardware. The role includes evolving compiler lowering infrastructure, developing optimization algorithms, and partnering with hardware teams to co-design instructions, memory architectures, and computing abstractions. The engineer will also guide cross-functional delivery, raise engineering standards through reviews and mentorship, solve complex compiler and performance issues, and develop documentation and best practices.
Requirements
- Bachelor’s degree with 10+ years, Master’s degree with 8+ years, or PhD with 5+ years of industry experience.
- Strong background in compiler design and optimization techniques.
- Experience developing and optimizing software for high-performance computing systems.
- Familiarity with PyTorch, TensorFlow, or JAX.
- Familiarity with hardware architectures such as CPUs, GPUs, TPUs, and NPUs.
- Strong analytical and problem-solving skills.
- Excellent communication and interpersonal skills.
- Ability to work independently and as part of a team.
- Inclusive approach, adapting communication and working style to varied situations and global norms.
- Curiosity and resilience when approaching challenges, with a willingness to seek data to build understanding.
- Collaborative approach to building relationships, offering support, and welcoming others’ approaches.
- Innovative and creative mindset, with a proactive approach to exploring ideas and adapting to change.
Nice To Haves
- Experience with LLVM or MLIR.
Responsibilities
- Lead the architecture, design, and implementation of ML compilers for high-performance deep learning applications targeting next-generation AGI hardware platforms.
- Design and evolve staged lowering infrastructure to adapt to changing workload requirements and novel hardware features.
- Invent and implement optimization algorithms for data locality, memory scheduling, kernel fusion, and code generation to minimize energy consumption and maximize performance on AI accelerator systems.
- Bridge compiler and hardware teams by co-designing instructions, memory architectures, and computing abstractions, and ensuring the compiler fully uses them.
- Influence and align hardware, runtime, ML framework, and research teams to define and deliver ML compiler features and improvements.
- Raise engineering standards through design and code reviews, mentoring, and setting technical standards for compiler development.
- Troubleshoot and debug complex compiler and performance issues, guiding the team to root causes and durable solutions.
- Shape compiler documentation, user guides, and best practices.
Benefits
- Medical, dental, and vision benefits.
- 401(k).
- Incentive opportunities based on individual and company performance.
- Charitable giving match and opportunities to participate in community activities.
- Four or more weeks of paid time off per year, plus holidays and sick leave.
- Fertility care or adoption stipend, caregiver support, and medical travel support.
- On-demand wellness apps and free confidential therapy sessions.
- Onsite café and gym, plus virtual fitness classes.
- Flexible work environment.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
