Cyvl is looking to solve the problem of optimizing data curation and annotation workflows for their Machine Learning team, and to develop platforms and tooling that empower the team to move quickly and efficiently.
Requirements
- Strong hands-on experience with Kubernetes and container orchestration for ML workloads.
- Experience with the AWS SageMaker suite of tools
- Familiarity with modern data labeling and management platforms (e.g., Label Studio, Kili, Scale AI, CVAT, Prodigy, Postgres, etc.).
- Experience designing, maintaining, and scaling ML pipelines and tooling.
- Proficiency in Python and experience with ML libraries (e.g., PyTorch, TensorFlow, scikit-learn).
- Experience with the Go programming language
- Experience with experiment tracking tools (e.g., MLflow, Weights & Biases).
Responsibilities
- Build and maintain scalable pipelines for data ingestion, preprocessing, labeling, and metadata management.
- Centralize all ML annotations, datasets, and labels using best-in-class data management and labeling tools.
- Evaluate and integrate third-party tools and frameworks to increase efficiency of the ML development process.
- Contribute to infrastructure decisions and promote best practices across the MLOps lifecycle.
- Design and maintain platforms that accelerate ML experimentation, hyperparameter tuning, and training workflows.
- Collaborate with ML engineers to streamline and automate deployment of models to production environments.
Other
- 3+ years of experience in an MLOps or related role, supporting a team of at least 3 ML engineers.
- Excellent communication and collaboration skills, with the ability to work effectively across teams.
- Self-motivated, self-starter with a zeal to win
- Great communicator; strong oral and written skills
- Ability to think creatively
