About the job
About Us
Lightricks is an innovative AI-driven company dedicated to transforming imagination into reality. Our flagship technology, LTX-2, is an open-source generative video model designed to produce expressive, high-fidelity video content at remarkable speeds. This technology not only powers our acclaimed products but also supports a growing network of partners through API integrations.
Our most popular products, including Facetune and LTX Studio, are utilized by hundreds of millions of users globally. We pride ourselves on merging deep research with user-centric design and comprehensive execution to shape the future of creative expression.
Your Role
As a Senior ML Software Engineer focused on low-level and CUDA optimizations, you will be instrumental in designing, enhancing, and scaling Lightricks' machine learning inference systems. You will tackle complex technical challenges at the intersection of GPU acceleration, systems architecture, and machine learning deployment.
Your expertise in CUDA, C/C++, and performance tuning will be vital for improving runtime efficiency across diverse computing environments. You will collaborate with designers, researchers, and backend engineers to create production-grade ML pipelines optimized for latency, throughput, and memory usage, directly contributing to the infrastructure behind Lightricks' next-generation AI products. This position is perfect for an engineer with a strong systems-level mindset, extensive knowledge of GPU internals, and a desire to drive performance and efficiency boundaries in machine learning infrastructure.

