Nvidia Senior C++ Software Engineer - Apache Spark Solution 

China, Shanghai 

597449284

You will work with the open source community to accelerate Apache Spark for data science. Apache Spark is the most popular data processing engine in data centers for data science. We aim to dramatically accelerate Apache Spark use cases without application code changes. You will work on open source libraries including Spark-RAPIDS ( ), RAPIDS ( ), and Velox ( ).

What you'll be doing:

• Design and implement native Spark execution engine using RAPIDS, Velox, UCX and other related libraries.

• Design and implement solutions to optimize data exchange between Velox and RAPIDS libraries

• Enhance Velox OSS library for improved performance and Spark compatibility

• Contribute to RAPIDS library for large-scale adoptions in major enterprises

• Conduct performance benchmarking and profiling to achieve speed-of-light performance

• Working with a team of exceptional engineers including PMC and Committers of Apache Spark, Apache Hadoop, Apache Hive, and Apache Arrow

• Presenting technical solutions in industry conferences and meetups

What we need to see:

• BS, MS, or PhD in Computer Science, Computer Engineering, or closely related field

• 8+ years of work or research experience in software development

• 3+ years hands-on development experience with Velox, RAPIDS or similar data processing frameworks in memory management techniques and data serialization

• Exceptional C++ development experience in design, programming, testing, anddebugging

• Design and development expertises in columnar data processing with SIMD (Single Instruction, Multiple Data) and vectorization techniques

• Familiarity with operating systems and software development environments for ARM

• Proven technical skills in designing and implementing high-quality distributed systems

• Able to work successfully with multi-functional teams across organizational boundaries and geographies

• Highly motivated with strong communication skills

Ways to stand out from the crowd:

• Committership at major open source big-data projects

• Working experience with GPU-accelerated libraries (CUDA, cuBLAS, NCCL, RAPIDS, UCX)