Lightricks is an AI-first company with a mission to bridge the gap between imagination and creation. At our core is LTX-2, an open-source generative video model, built to deliver expressive, high-fidelity video at unmatched speed. It powers both our own products and a growing ecosystem of partners through api integration.
Our flagship products include Facetune and LTX Studio, used by hundreds of millions of users worldwide. We combine deep research, user-first design, and end-to-end execution to bring the future of expression to all.
What you will be doingAs 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
We’re here to push the boundaries of what’s possible with AI and video - not for the buzz, but for the craft, the challenge, and the chance to make something genuinely new.
We believe in an environment where people are encouraged to think, create, and explore. Real impact happens when people are empowered to experiment, evolve, and elevate together. At Lightricks, every breakthrough starts with great people and a collaborative mindset. If you're looking for a place that combines deep tech, creative energy, and zero buzzword culture, you might be in the right place.
- We run daily door-to-door shuttles, offering Car-to-go subscriptions for several locations in central Israel, plus free parking and train-station pickups.
- We’re proud to have 2 chef-led restaurants on site by the legendary Machneyuda Group (yes, that Machneyuda!), plus a bakery nestled in the heart of our office, filled daily with the scent of fresh pastries.
- We empower employees with cutting-edge tools and learning opportunities to grow and succeed through workshops, access and training on platforms, subscriptions, and clear guidelines for responsible AI use.
Skills Required
- 5+ years of experience in high-performance software engineering
- Advanced proficiency in CUDA, C/C++, and Python
- 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
What We Do
Lightricks is returning creative intelligence and power to the people who imagine and create by building open, efficient AI models and products that understand and generate the visual world. Our vision: push the limits of technology to reimagine the way creators express themselves. Big mission. Fast-moving team. Come build it with us. At our core is LTX- an open-source generative video model built to deliver expressive, high-fidelity video at unmatched speed. It powers our own products and a growing ecosystem of creative partners worldwide. We're one of the few companies globally building our own multimodal foundation models, competing directly with the world's largest AI labs. Startup speed. Experienced leadership. A product people already love. Backed by a proven business model and unicorn-scale resources. We were founded by four computer-science PhDs who never stopped thinking like researchers. That mindset still defines us: deep technical ambition, a bias toward building, and a belief that the best creative tools haven't been invented yet. The team has done it before. Lightricks' suite of apps, including the famous Facetune, has over 500 million downloads worldwide and has won numerous prestigious awards, including Apple's App of the Year, the Apple Design Award and both Apple and Google Play's Best of the Year. What makes us "us" - At Lightricks, innovation starts with people, not buzzwords. We move fast, speak plainly, and take real ownership. Impact here comes from passion, curiosity, and initiative, and from raising the bar for yourself and the people around you. We believe the best work happens together. The culture here is genuinely collaborative, people share knowledge, back each other up, and win as a team. When things click, everyone feels it. You'll have what you need to do your best work: unrestricted access to compute, tools, and resources. We're AI-native in practice- first access to the latest models, real infrastructure, and a team that learns together in real time. We move at the pace of AI, not just in what we ship, but in how we think and work. Priorities shift, the market moves, and we move with it. If you thrive on change, adapt quickly, and want to be part of a team that keeps up, you'll feel right at home. We build, break, iterate, repeat. What matters here is how you think, what you're curious about, and where you want to go.
Why Work With Us
Native frontier AI, built in-house, competing with the largest players. A product already in market, already winning customers, with a B2B story just getting started. AI-first and people-first in how we operate. Unrestricted access to tools and compute. People who push you and celebrate when you win. The right moment to be at the front.
