Scale synthetic coding data to trillions of tokens with large-scale docker verification. Distill the intelligence of flagship models into flash models through synthetic data generation. Optimize mid-training data mixtures to boost the ceiling for RL.
Build highly reliable, efficient, and easy to use infrastructure that runs all our evaluations at scale.
Scale synthetic coding data to trillions of tokens with large-scale docker verification. Distill the intelligence of flagship models into flash models through synthetic data generation. Optimize mid-training data mixtures to boost the ceiling for RL.
Design and implement the systems backing all RL workloads at SpaceXSI, from small scale ablations to production training runs. Profile, debug, and optimize end-to-end training performance. Improve scalability and observability of the RL stack.
Design and optimize our inference stack for all shapes of RL workloads at SpaceXSI, from small scale ablations to production training runs. Analyze, profile and address performance bottlenecks in large scale RL systems.
Design and implement the systems backing all RL workloads at SpaceXSI, from small scale ablations to production training runs. Profile, debug, and optimize end-to-end training performance. Improve scalability and observability of the RL stack.
Design and run rigorous experiments that turn research ideas into measurable gains in model capability. Improve model recipes through data quality, deduplication, and mixture experiments.
Design and run rigorous experiments that turn research ideas into measurable gains in model capability. Improve model recipes through data quality, deduplication, and mixture experiments.
Design, build, and maintain large-scale distributed data pipelines that ingest, process, and annotate real-world and synthetic audio, so the training and evaluation systems get reliable, high-quality data.
Design, build, and optimize large-scale distributed systems for multimodal pre-training, post-training, inference, data processing, and tokenization at web/petabyte scale.
Showing 10 of 94 jobs
Show more jobs
Palo Alto, Canada
Palo Alto, USA
London, GB
Dublin, IE