Senior Systems Software Engineer, CUDA-Accelerated Spark

NVIDIA Corporation; Redmond (WA); On-site; USD 184,000 - 357,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation is seeking a Sr. Systems Software Engineer for the Apache Spark Acceleration group in Redmond, WA.

The role focuses on enabling CUDA-based execution for Spark operations, accelerating DataFrames and I/O across Parquet/ORC/JSON, and collaborating with distributed systems and open source communities to advance RAPIDS and related libraries. The position requires extensive experience in C++, Java, and Scala, with a background in data platform development and enterprise customer

Qualifications

• 9+ years of experience in software development.
• 5+ years hands on experience with data platform development.
• BS/MS/PhD in computer science or a related field (or equivalent experience).
• Proficiency in C++, Java, Scala.
• Experience supporting enterprise customers.
• Familiarity with the open source data platform ecosystem is a plus (Apache Spark, Velox, Presto, Apache Arrow, Apache DataFusion, etc.).
• Experience using AI tools in software development.

Responsibilities

• Enable C++ native execution of Spark operations on CUDA.
• Develop CUDA/C++ libraries to accelerate DataFrames and I/O operations on common file formats such as Parquet, ORC and JSON.
• Collaborate with distributed systems teams to craft solutions to distributed processing problems at large scale.
• Work with open source communities to enhance libraries like RAPIDS, CCCL and UCX through technical discussion and code contributions.
• Provide recommendations and feedback to teams regarding decisions surrounding infrastructure, CI and testing strategy.
• Build, test and optimize across different platforms.

Skills

C++

Java

Scala

Education

BS/MS/PhD in computer science or related field

Tools

Apache Spark

RAPIDS

UCX

Velox

Job description

NVIDIA Corporation is seeking a Sr. Systems Software Engineer for the Apache Spark Acceleration group in Redmond, WA.

The role focuses on enabling CUDA-based execution for Spark operations, accelerating DataFrames and I/O across Parquet/ORC/JSON, and collaborating with distributed systems and open source communities to advance RAPIDS and related libraries. The position requires extensive experience in C++, Java, and Scala, with a background in data platform development and enterprise customer