Runware logoRunware logo

Lead Senior Machine Learning Engineer

RunwareRemote — United Kingdom
Remote Full-time

Clicking Apply Now takes you to AutoApply where you can tailor your resume and apply.


Experience Level

Senior

Qualifications

Required QualificationsDemonstrated experience in delivering machine learning systems to production environments. Proficient in Python with extensive hands-on experience using PyTorch. Experience with diffusion models, LLMs, or multimodal architectures. Practical skills in fine-tuning large models using techniques such as LoRA, PEFT, and adapters. Expertise in optimizing inference workloads within GPU environments. Strong foundation in model evaluation, experimentation, and monitoring. Adept at diagnosing performance, memory, and reliability challenges in production settings. Possess a systems-thinking approach to understand how ML decisions influence infrastructure. High level of ownership and comfort navigating a dynamic startup environment. Preferred QualificationsExperience with vLLM or custom inference servers. Familiarity with Kubernetes or containerized ML workloads. Background in high-throughput distributed systems. Experience in AI-driven media generation (image, video, audio). Experience building internal ML tools or developer-facing APIs. Competence with CUDA/C++ kernels.

About the job

Step into the future of artificial intelligence with Runware as a Senior Machine Learning Engineer, where you will spearhead the development of groundbreaking AI solutions across multiple media formats, including text, images, videos, 3D, and audio. Our innovative AI media creation platform is designed to transform the landscape of content generation.

In this pivotal role, you will oversee essential projects, managing the complete lifecycle from research and experimentation through to production deployment and performance evaluation. Your contributions will be instrumental in enhancing the capabilities of our platform and improving the experiences of users who rely on our state-of-the-art AI technologies.

Key Responsibilities

  • Integrate open-source and third-party models into our inference platform.
  • Lead fine-tuning initiatives including LoRA, adapters, PEFT, and domain adaptation.
  • Optimize inference workloads focusing on latency, batching, memory efficiency, and throughput.
  • Benchmark model quality against cost and performance across various modalities.
  • Enhance inference startup times and stability under heavy load.
  • Develop evaluation frameworks and internal tools for model validation.
  • Collaborate closely with Infrastructure and Backend teams to create scalable serving systems.
  • Monitor production performance and drive continuous optimization efforts.
  • Mentor junior engineers and elevate the ML engineering standards within the team.

About Runware

Runware is a forward-thinking technology company committed to revolutionizing the media landscape through advanced AI solutions. Our remote-first team collaborates to push the boundaries of what is possible in content creation, leveraging the latest in machine learning and artificial intelligence.

Similar jobs

Browse all companies, explore by city & role, or SEO search pages.

Tailoring 0 resumes

We'll move completed jobs to Ready to Apply automatically.