Tech Stack
NumpyPySparkPythonPyTorchScikit-LearnSQLTensorflow
About the role
- Develop and deploy scalable recommendation algorithms (collaborative filtering, content-based, hybrid)
- Translate business objectives into data science problems and deliver solutions that drive measurable outcomes
- Work with petabyte-scale datasets to train, validate, and optimize ML models (ranking, retrieval, embeddings)
- Build end-to-end ML pipelines (training, validation, CI/CD, deployment, monitoring) using MLOps best practices
- Collaborate with product, engineering, and analytics teams to integrate models into production systems
- Optimize model inference for latency, scale, and cost-efficiency
- Define technical problem statements and hypotheses; communicate results and drive strategy
Requirements
- 10 years of experience working as a Data Scientist
- Hands-on experience with enterprise data science solutions, preferably in retail, inventory management, or operations research
- Proficiency in Python, SQL, and PySpark
- Experience with production-level coding and deployment practices
- Familiarity with basic machine learning techniques and mathematical optimization methods
- Proficient in data science libraries and ML pipelines such as NumPy, SciPy, scikit-learn, MLlib, PyTorch, TensorFlow
- Self-starter with an ownership mindset and ability to work with minimal supervision