About the Role
We are looking for Machine Learning engineers to work on our platform and inference team who are passionate about generative models and creative applications of AI. In particular, we are looking for people who have experience of developing model serving pipelines to operate at scale and have knowledge of state of the art techniques for optimisation and feature development. We want highly creative ML engineers who are motivated to push the boundaries of generative models. You will have access to state-of-the-art high performance computing resources and you will be able to work alongside top researchers and engineers to truly make an impact in the fast growing world of generative AI.
Responsibilities:
Lead efforts to drive the design development and production of customer-facing ML systems, with specific reference to inference and API environments
Work with the Platform and Inference teams on building pipelines for the next generation of models, where you may assist with areas such as optimization, model tuning and deployment, HPC clusters, tooling
Be a strategic thought partner for leaders across the organization on driving business impact through machine learning
Work on the Commercial side - productionizing generative models, and building the infrastructure to serve them at scale
Be part of the team to bring new Stability models and pipelines into existence for API customers
Prototype and productionize inference platform improvements and new features
Qualifications:
5+ years working on machine learning projects, including inference and pipeline development
Solid knowledge of Python scientific stack, PyTorch and at least one high-performance inference framework (e.g. TensorRT)
Experience profiling and optimizing deep neural networks, including knowledge of GPU profiling tools such as NVIDIA Nsight
Familiarity with Python-based image manipulation/encoding/decoding frameworks, such as OpenCV
Experience with cloud orchestration systems such as Kubernetes and cloud providers such as AWS, GCP, and Azure
Ability to write robust and maintainable client-server architectures and APIs
Ability to rapidly prototype solutions and iterate on them with tight product deadlines
Experience with training and/or deploying ML models with Amazon AWS (Sagemaker a plus) or Google Cloud
Strong communication, collaboration, and documentation skills
Experience with building interactive web demos that serve generative ML models
Experience with the open-source ML ecosystem (HuggingFace, W&B, etc.)
Experience with Linux and command line tools