Senior Data Scientist

Design, build, and maintain end-to-end machine learning models for ETA/ATA prediction and message-based status extraction in supply chain logistics.

Develop and deploy NLP/LLM pipelines for text extraction and entity recognition from noisy, real-world logistics data; manage automated training, retraining, and model monitoring.

Drive operational improvements by replacing manual processes with ML automation and translate model performance into measurable business impact while mentoring other data scientists.

Experience building and deploying production ML models with time-series forecasting, regression, classification, and NLP techniques.

Strong proficiency in Python and SQL, with experience in data infrastructure including AWS (S3, EC2) and orchestration tools like Airflow.

Experience with setting up and maintaining model monitoring and observability tools (e.g., Grafana).

Work Experience Required: Not explicitly mentioned in the JD.

Experienced working with noisy, large-scale real-world datasets in logistics or supply chain environments, accustomed to closing gaps between offline and production model performance.

Capable of independently making build-versus-buy and architectural decisions in ML solutions, with a record of reducing manual interventions through automation.

Skilled in cross-functional collaboration and mentoring, able to communicate model impact effectively to technical and non-technical stakeholders.