Manager, Software Engineering, MTIA Software
Bellevue, WA | Menlo Park, CA | New York, NY
Meta
Giving people the power to build community and bring the world closer together
The MTIA (Meta Training & Inference Accelerator) Software team is part of AI Infra PyTorch org. The team’s mission is to explore, develop and help productize high-performance software and hardware technologies for AI at datacenter scale. The team co-optimizes both SW (e.g., algorithms and numerics) and HW (e.g., platform and network) to come up with balanced system design. To develop new systems, requires understanding performance bottlenecks on existing systems. As a result, the team invests significantly into optimizing AI production models on existing systems. This has resulted in TCO wins for all key AI services.
Team has been developing AI frameworks to accelerate Meta’s DL/ML workloads on the specialized MTIA AI accelerator hardware in a highly performant and flexible way. As part of the AI acceleration software stack, we develop kernel libraries exploiting various hardware architectural features, achieving high performance for our inference and training workloads.Manager, Software Engineering, MTIA Software Responsibilities
Individual compensation is determined by skills, qualifications, experience, and location. Compensation details listed in this posting reflect the base hourly rate, monthly rate, or annual salary only, and do not include bonus, equity or sales incentives, if applicable. In addition to base compensation, Meta offers benefits. Learn more about benefits at Meta.
Team has been developing AI frameworks to accelerate Meta’s DL/ML workloads on the specialized MTIA AI accelerator hardware in a highly performant and flexible way. As part of the AI acceleration software stack, we develop kernel libraries exploiting various hardware architectural features, achieving high performance for our inference and training workloads.Manager, Software Engineering, MTIA Software Responsibilities
- Grow a team of domain experts in high performance deep learning kernel development, hardware/software codesign technologies.
- Manage diverse teams of researchers and developers, help them develop their careers, assigning them to projects tailored to their skill levels, long-term skill development, personalities, and work styles.
- Communicate and collaborate effectively with cross-functional hardware and software engineering teams.
- Champion engineering and operational excellence, establishing metrics and process for regular assessment and improvement.
- Set clear expectations and create a positive work environment based on accountability, in collaboration with the engineering and management teams.
- Operate strategically and tactically. Develop the vision and strategy to help set direction for the team, while staying on top of the day-to-day software development.
- Work closely with dedicated recruiting staff to expand the team, including sourcing candidates, interviewing candidates, participating in conferences/events, and on-boarding new employees.
- At least 5 years of experience in managing a software team in a fast-paced capacity.
- Demonstrated experience in managing other managers.
- Proven understanding and experience executing full product life-cycles (prototyping, deployment, and support).
- Accelerator (GPU/ASIC) kernel development and optimization.
- Experience in accelerating libraries on AI hardware, similar to cuBLAS, cuDNN, CUTLASS, HIP, ROCm etc.
- Experience with different programming models for high-performance computations, e.g. GPU CUDA programming or OpenCL or OpenMP programming.
- Experience working closely with hardware architectures such as Intel SIMD, GPU, RISC-V, AI Accelerators etc.
- Experience in hardware-software development environments such as simulators, FPGA emulators etc.
- Knowledge of ML frameworks like PyTorch, TensorFlow, ONNX, MXNet, etc.
Individual compensation is determined by skills, qualifications, experience, and location. Compensation details listed in this posting reflect the base hourly rate, monthly rate, or annual salary only, and do not include bonus, equity or sales incentives, if applicable. In addition to base compensation, Meta offers benefits. Learn more about benefits at Meta.
Job stats:
0
0
0
Categories:
Engineering Jobs
Leadership Jobs
Tags: Architecture CUDA cuDNN Deep Learning Engineering FPGA GPU Machine Learning MXNet ONNX OpenMP Physics Prototyping PyTorch SIMD TensorFlow VR
Perks/benefits: Career development Conferences Equity / stock options Flex hours Health care Salary bonus Team events
Region:
North America
Country:
United States
More jobs like this
Explore more career opportunities
Find even more open roles below ordered by popularity of job title or skills/products/technologies used.
Business Intelligence Developer jobsPrincipal Data Scientist jobsData Engineer II jobsStaff Data Scientist jobsBI Developer jobsPrincipal Data Engineer jobsCopywriter - Freelance AI Tutor jobsData Manager jobsJunior Data Analyst jobsData Scientist II jobsData Science Manager jobsResearch Scientist jobsBusiness Data Analyst jobsLead Data Analyst jobsSr. Data Scientist jobsSr Data Engineer jobsData Science Intern jobsSenior Artificial Intelligence/Machine Learning Engineer - Remote, Latin America jobsBI Analyst jobsSenior AI Engineer jobsJunior Data Engineer jobsData Engineer III jobsSoftware Engineer, Machine Learning jobsJunior Data Scientist jobsData Specialist jobs
Linux jobsSnowflake jobsEconomics jobsOpen Source jobsHadoop jobsPhysics jobsRDBMS jobsComputer Vision jobsJavaScript jobsAirflow jobsMLOps jobsBanking jobsKafka jobsScala jobsData Warehousing jobsNoSQL jobsData warehouse jobsSAS jobsGoogle Cloud jobsKPIs jobsOracle jobsGitHub jobsPostgreSQL jobsTerraform jobsR&D jobs
Streaming jobsScikit-learn jobsClassification jobsScrum jobsCX jobsData Mining jobsPandas jobsLooker jobsIndustrial jobsJira jobsPySpark jobsDistributed Systems jobsRobotics jobsJenkins jobsRedshift jobsBigQuery jobsReact jobsMicroservices jobsdbt jobsMatlab jobsMySQL jobsUnstructured data jobsE-commerce jobsData strategy jobsGPU jobs