ML Engine Software Engineer

Who we are

Lightricks, an AI-first company, is revolutionizing how visual content is created. With a mission to bridge the gap between imagination and creation, Lightricks is dedicated to bringing cutting-edge technology to the creative and business spaces.

Our advanced AI photo and video generation models, including our open-source LTXV model, power our apps and platforms including Facetune, Photoleap, Videoleap, and LTX Studio, allowing creators and brands to leverage the latest research breakthroughs, offering endless control over their creative potential. Our influencer marketing platform, Popular Pays, provides creators the ability to monetize their work and offers brands opportunities to scale their content through tailored creator partnerships.

The ML Engine team is dedicated to driving innovation in machine learning (ML) by enhancing model efficiency and accelerating development cycles. This work is essential to keeping Lightricks at the forefront of the competitive generative AI landscape. The team focuses on developing and optimizing backend systems that support ML inference, directly impacting our products' speed and scalability.

What you will be doing

As ML Engine SW Engineer, you will play a crucial role in shaping the system design, backend architecture, and overall performance of Lightricks’ ML inference systems. We collaborate with cross-functional teams, including designers, developers, and researchers. The role offers the chance to make a significant impact on Lightricks’ core production systems. You’ll have the opportunity to develop and optimize critical backend features and work across diverse technical areas, contributing directly to the company's success. This hands-on role involves working extensively with Python, ComfyUI, system optimizations, and cloud infrastructure.

This position is perfect for a skilled backend engineer passionate about driving efficiency and innovation in machine learning. Join us to make an impactful difference in Lightricks’ AI journey!

Core Responsibilities

• Develop and maintain Lightricks' ML inference engine
• Drive improvements in system efficiency, monitoring, and performance
• Work directly with internal engine users to gather requirements and feedback
• Implement enhancements and optimizations within ComfyUI and other backend frameworks

Day-to-Day Responsibilities

• Design and optimize backend systems to support efficient ML model inference
• Work with cloud infrastructure, networking, and both CPU and GPU architecture
• Enhance the efficiency and observability of our inference engine, supporting various high-demand applications
• Collaborate closely with engine users, designers, developers, and researchers to refine and improve system capabilities
• Contribute to the ComfyUI codebase, ensuring a scalable, user-friendly interface for machine learning operations
• Navigating and contributing to a large, complex existing codebase
• Addressing complex issues with creativity and efficiency

Your skills and experience

• 5+ years of experience with Python in production environments
• Strong understanding of system architecture principles
• Proven familiarity with machine learning frameworks and methodologies
• Independent leadership with a proactive approach to problem-solving
• Strong analytical skills for diagnosing and addressing complex technical challenges
• A collaborative, team-player mindset that thrives in cross-functional environments

Preferred Requirements

• Knowledge of CPU/GPU architecture and experience with low-level optimizations
• Experience with image processing and computer vision
• Experience contributing to large, open-source projects