remote
Applied Scientist, Amazon Redshift - Amazon Web Services
Software Engineer
Applied Scientist focused on building deep learning models to predict query resource consumption for Amazon Redshift, driving intelligent workload management at scale using Python, ML, and AWS services.
About the role
Key Responsibilities
- Design, develop, and deploy deep learning models that forecast query resource usage in Amazon Redshift.
- Collaborate with data engineering and product teams to integrate predictive models into workload management pipelines.
- Analyze large-scale query logs, engineer features, and optimize model performance for real-time inference.
- Experiment with novel ML techniques, conduct A/B tests, and iterate on model accuracy and latency.
- Document model architecture, training procedures, and evaluation metrics for internal and external stakeholders.
Requirements
- Strong background in machine learning and deep learning, with experience in Python and frameworks such as TensorFlow or PyTorch.
- Proficiency in SQL and experience working with large-scale data warehouses, preferably Amazon Redshift.
- Hands‑on experience with AWS services (SageMaker, Lambda, Glue, etc.) for model training and deployment.
- Excellent analytical skills, ability to translate business problems into data‑driven solutions.
- Effective communication skills and a collaborative mindset for cross‑functional teams.
Skills
pythonmachine learningdeep learningawssql