Applyπ Canada, Latin America, Alabama, Arizona, California, Colorado, Connecticut, Florida, Georgia, Illinois, Indiana, Massachusetts, Minnesota, Nevada, New Jersey, New York, North Carolina, Oregon, Pennsylvania, Rhode Island, Tennessee, Texas, Utah, Virginia, Washington
πΈ 140000.0 - 220000.0 USD per year
π Retail AI
π’ Company: Lily AI
- 10+ years in building large-scale machine learning solutions and ML Ops practices.
- Working with LLM APIs and serving LLMs in-house at scale.
- Proficiency in Kubernetes, RDBMS, and API-driven development.
- Experience in model serving in low-latency, high-throughput use cases.
- Knowledge of observability, data pipeline design, service scaling, and cost optimization.
- Strong emphasis on code hygiene, including review, documentation, testing, and CI/CD practices.
- Proficiency in Python and PyTorch.
- Extensive experience with the scientific Python ecosystem.
- Proficiency in cloud-native application development.
- Action-oriented with the ability to articulate complex concepts.
- Define, design, and maintain scalable Machine Learning data pipelines, training infrastructure, and inference systems.
- Optimize, benchmark, and productionize deep learning models to extract high-value product attributes.
- Drive cost efficiency and throughput improvements, owning relevant KPIs.
- Promote and implement software engineering best practices across the team.
- Shape and evolve the technical stack to meet business and technical needs.
- Transition research prototypes into robust, production-ready systems.
- Deploy, monitor, and continuously improve models in production environments.
- Optimize model performance, focusing on memory usage and latency.
- Automate workflows by building efficient pipelines and orchestration frameworks.
- Develop tools and shared libraries to boost team productivity.
PythonKubeflowKubernetesMachine LearningMLFlowPyTorchAzure
Posted 27 days ago
Apply