Senior Machine Learning Engineer

4 months ago
Full-time
Senior
Software Development
RUNWARE

RUNWARE

RUNWARE provides an affordable API that enables AI developers to efficiently run image, video, and custom generative AI models without the need for extensive infrastructure or machine learning expertise.

Internet Software & Services
1-10
Founded 2023

Description

  • Integrate open-source and third-party models into the inference platform.
  • Lead fine-tuning initiatives using LoRA, adapters, PEFT, and domain adaptation techniques.
  • Optimize inference workloads for latency, batching, memory efficiency, and throughput.
  • Benchmark model quality, cost, and performance across multiple modalities.
  • Improve inference startup times and stability under high load.
  • Build evaluation frameworks and internal tooling for model validation.
  • Collaborate with Infrastructure and Backend teams on scalable serving systems.
  • Monitor production performance and drive continuous optimization.
  • Mentor engineers and help raise the ML engineering standards across the team.

Requirements

  • Proven experience delivering machine learning systems to production environments.
  • Strong low-level Python skills and deep hands-on experience with PyTorch.
  • Experience working with diffusion models, LLMs, or multimodal architectures.
  • Practical experience fine-tuning large models using LoRA, PEFT, adapters, or similar methods.
  • Experience optimizing inference workloads in GPU environments.
  • Strong understanding of model evaluation, experimentation, and monitoring.
  • Ability to debug performance, memory, and reliability issues in production.
  • Strong systems thinking and understanding of how ML decisions impact infrastructure.
  • High ownership and comfort operating in a fast-paced startup environment.
  • Experience with vLLM or custom inference servers is preferred.
  • Experience with Kubernetes or containerised ML workloads is preferred.
  • Experience working in high-throughput distributed systems is preferred.
  • Background in AI media generation, including image, video, or audio, is preferred.
  • Experience building internal ML tooling or developer-facing APIs is preferred.
  • Experience with CUDA/C++ kernels is preferred.

Benefits

  • Remote-first setup with the ability to work from home anywhere the company can employ you.
  • Flexible hours outside core collaboration blocks.
  • Generous paid time off, including vacation, sick days, and public holidays.
  • Meaningful stock options.
  • Paid family leave for maternity, paternity, and caregiver time.
  • Company retreats twice a year in inspiring locations.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Lead Machine Learning Scientist, Business Banking

Monzo 1K-5K Banks

Monzo is hiring a Lead Machine Learning Scientist for its Business Banking team to build and ship ML and GenAI models that improve products for UK small businesses.

Generative AI Go LLM Machine Learning Microservices MLOps Python Scikit-learn SQL
21 hours, 5 minutes ago

Machine Learning Systems Engineer

Motional 1K-5K Automotive

Motional is hiring a Machine Learning Systems Engineer for its ML Acceleration team to improve the systems that enable large-scale frontier model training.

Machine Learning Python PyTorch
21 hours, 35 minutes ago

Staff ML Engineer (ML/AI)

Lyra Health 1K-5K Health Care Providers & Services

Lyra Health is hiring a Staff ML/AI Engineer to define the architecture and technical strategy for enterprise-scale machine learning and generative AI platforms supporting clinically precise, reliable mental health products.

AWS Celery CI/CD Docker Generative AI HIPAA Java Kafka Kotlin Kubernetes Machine Learning Microservices MLOps Python REST API
2 days, 22 hours ago

Applied AI/ML Engineer

Boundless Internet Software & Services

Boundless is hiring an Applied AI/ML Engineer to build and ship end-to-end AI products on its GPU inference fleet, from low-latency serving through reinforcement-learning post-training and production evaluation.

Docker Kubernetes Python PyTorch Reinforcement Learning
2 days, 22 hours ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers