Senior Software Engineer - Research

LTX is pioneering a new era of visual rendering tools that empower professionals and creators across creative industries such as Advertising, Creative Marketing, 3D Design, Animation, and more. Our latest release, LTX-2, unites high-quality synchronized audio and video generation, native 4K fidelity, long sequences, and radical efficiency - all in a single, production-ready system. At LTX, we’re building a new foundation that transforms the relationship between creation and technology.

 As an ML Software Engineer with a focus on low-level and CUDA-based optimizations, you will play a key role in shaping the design, performance, and scalability of Lightricks’ machine learning inference systems. You’ll work on deeply technical challenges at the intersection of GPU acceleration, systems architecture, and ML deployment.
Your expertise in CUDA, C/C++, and performance tuning will be crucial in enhancing runtime efficiency across heterogeneous computing environments. You’ll collaborate with designers, researchers, and backend engineers to build production-grade ML pipelines that are optimized for latency, throughput, and memory use, contributing directly to the infrastructure powering Lightricks' next-generation AI products.
This role is ideal for an engineer with strong systems-level thinking, deep familiarity with GPU internals, and a passion for pushing the boundaries of performance and efficiency in machine learning infrastructure.

• Design and implement highly optimized GPU-accelerated ML inference systems using CUDA and low-level parallelism techniques
• Optimize memory, compute, and data flow to meet real-time or high-throughput constraints
• Improve the performance, reliability, and observability of our inference backend across diverse compute targets (CPU/GPU)
• Collaborate with cross-functional teams (including researchers, developers, and designers) to deliver efficient and scalable inference solutions
• Contribute to ComfyUI and internal infrastructure to improve usability and performance of model execution flows
• Investigate performance bottlenecks at all levels of the stack—from Python to kernel-level execution
• Navigate and enhance a large, complex, production-grade codebase
• Drive innovation in low-level system design to support future ML workloads

• 5+ years of experience in high-performance software engineering
• Advanced proficiency in CUDA, C/C++, and Python, especially in production environments
• Deep understanding of GPU architecture, memory hierarchies, and optimization techniques
• Proven track record of optimizing compute-intensive systems
• Strong system architecture fundamentals, especially around performance, concurrency, and parallelism
• Ability to independently lead deep technical investigations and deliver clean, maintainable solutions
• Collaborative and team-oriented mindset, with experience working across functional teams

• Experience with low-level profiling and debugging tools (e.g., Nsight, perf, gdb, VTune)
• Familiarity with machine learning frameworks (e.g., PyTorch, TensorRT, ONNX Runtime)
• Contributions to performance-critical open-source or ML infrastructure projects
• Experience with cloud infrastructure and GPU scheduling at scale