Why work at Voltron Data?
- We are Going for Impact: We are a Series A, venture-backed startup assembling a global team to build a new foundation for data analytics with Apache Arrow. This foundation will usher in a wave of innovation in data processing that can take full advantage of the speed and efficiency offered by modern hardware.
- We are Committed to Bridging Open Source Communities: We are a collection of open source maintainers who have been driving open source ecosystems over the last 15 years, particularly in the C++, Python, and R programming ecosystems.
- We are Building a Diverse, Inclusive Company: We are creating a representative, equitable, and respectful workplace that prioritizes employee growth. Everyone at Voltron Data is bought into the company’s success; all voices are critical to shaping the organization’s future.
Below is a rough timeline of where you can expect to be at different points during your career path starting in this position.
- Spending time learning about the Apache Arrow memory layout, compute primitives, and APIs.
- Familiarizing yourself with the different partners for compute on Apache Arrow.
- Helping to define profiling and performance optimization strategies.
Within a month:
- Architecting / designing performant compute kernels that leverage vectorization.
- Leading technical discussions, building technical design documents, and reviewing work in kernel development.
- Collaborating with other teams at Voltron Data to ensure that compute kernel APIs can be utilized as effectively and efficiently as possible.
- Collaborating with the open source Apache Arrow ecosystem to make Arrow the most performant data analytics solution possible.
Within 6 months:
- Architecting and designing a plan to support multiple architectures and platforms.
- Proposing plans to balance prioritization between development of new kernels and optimization of existing kernels.
- Designing process to ensure kernels are consistently improving in performance and working across teams to address bottlenecks.
- Conduct profiling, scaling studies, parallelization and memory bandwidth analyses.
Within 12 months:
- Acting as a HPC software engineer tech leader within Voltron Data.
- Defining standard methodologies for compute kernel development and promoting these across the Voltron Data and Apache Arrow ecosystems.
- Ensuring that the compute kernels are as high quality as possible, balancing performance, usability, and maintainability.
- Developing strategies for addressing and improving performance as well as productivity requirements of teams across Voltron Data.
Previous experience that could be helpful:
- Building libraries in C++, especially using Modern C++.
- Using and/or building performance portability libraries on accelerator hardware or targeting multiple CPU instruction sets.
- Developing software for manycore computer architectures and GPUs, and/or optimizing software for vectorization, multithreading, GPU acceleration.
- Designing and implementing parallel/distributed algorithms.
- Developing, analyzing and optimizing performance of software in the HPC context.
- Benchmarking, code instrumentation, performance analysis and profiling.
- Contributions to open source projects or public code repositories.
US Compensation - The salary range for this role is between $140,000 to $165,000. We have a global market-based pay structure which varies by location. Please note that the base pay range is a guideline and for candidates who receive an offer, the exact base pay will vary based on factors such as actual work location, skills and experience of the candidate. This position is also eligible for additional incentives such as equity awards.