Member of Technical Staff — Diffusion Model

Location: Palo Alto

Department: engineer

About the Role

RadixArk is seeking a Member of Technical Staff — Diffusion Model to advance the frontier of generative modeling.

You will work on cutting-edge diffusion and flow-based models for image, video, and multimodal generation, pushing model quality, efficiency, and scalability. This role combines deep research thinking with strong engineering execution — from designing novel algorithms to training and deploying models at scale.

Your work will directly shape next-generation generative AI systems used by researchers, developers, and real-world applications.

This is a high-impact role for engineers and researchers who want to push the limits of generative models in both theory and practice.

Requirements

• 5+ years of experience in ML research or applied ML engineering

• Strong expertise in diffusion models or generative models (DDPM, DDIM, latent diffusion, flow matching, etc.)

• Deep understanding of deep learning fundamentals and optimization

• Proven experience training large-scale models on GPUs/TPUs

• Strong proficiency in PyTorch or JAX

• Experience implementing research ideas into working systems

• Strong mathematical foundation in probability, statistics, and optimization

• Ability to move from research prototypes to production-quality models

Strong Plus

• Publications in top-tier conferences (NeurIPS, ICML, ICLR, CVPR, etc.)

• Experience with large-scale distributed training

• Experience in multimodal generation (text-to-image, video, audio)

• Familiarity with transformer architectures and hybrid models

• Experience improving sampling speed and generation efficiency

• Contributions to open-source generative model projects

• Experience scaling models to billions of parameters

Responsibilities

• Design and develop next-generation diffusion and generative models

• Improve model quality, controllability, and sample efficiency

• Research and implement novel training and sampling methods

• Optimize models for large-scale distributed training

• Collaborate with systems teams to scale training and inference

• Translate research ideas into practical production systems

• Evaluate models using rigorous metrics and benchmarks

• Contribute to long-term research and product direction in generative AI

About RadixArk

RadixArk is an infrastructure-first AI company built by engineers who have shipped production AI systems, created SGLang (20K+ GitHub stars, the fastest open LLM serving engine), and developed Miles, our large-scale RL framework.

We build world-class systems for training and inference and partner with frontier AI teams and cloud providers. Our mission is to democratize access to frontier AI infrastructure and models.

Our team has coordinated training across 10,000+ GPUs, optimized kernels serving billions of tokens daily, and supported leading AI research and production workloads.

Join us to build generative models that matter — at real scale.

Compensation

We offer competitive compensation with meaningful equity, comprehensive benefits, and flexible work arrangements. Compensation depends on location, experience, and level.

Equal Opportunity

RadixArk is an Equal Opportunity Employer and welcomes candidates from all backgrounds.