Senior Data Scientist

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior Data Scientist based in India.

This is an opportunity to build and own production-grade machine learning solutions that solve complex, real-world supply chain problems.

You will work across the full ML lifecycle, from data pipelines and model development to deployment, monitoring, and retraining.

Your work will directly influence forecasting accuracy, operational efficiency, automation, and customer outcomes.

The role combines hands-on technical ownership with opportunities to guide other data scientists and engineers.

You’ll work with challenging, high-volume data including GPS signals, carrier information, and unstructured logistics messages.

Collaboration with product, engineering, and operations teams will be essential to turning technical improvements into measurable business value.

You’ll join a highly collaborative environment focused on building scalable, AI-driven solutions and proactive supply chain automation.

Accountabilities:

• Design, develop, and productionize machine learning models for ETA/ATA prediction and other forecasting, regression, and classification problems.
• Build NLP and LLM-based extraction pipelines for unstructured messages, including text extraction and entity recognition for status and ETA information.
• Own ML solutions end-to-end, covering data preparation, training, deployment, monitoring, retraining, and continuous improvement.
• Work with noisy, complex, real-world logistics data such as GPS pings, check calls, carrier feeds, and other operational datasets.
• Investigate differences between offline model performance and live production results, identify root causes, and implement corrective actions.
• Build and maintain automated training and retraining workflows using orchestration tools such as Airflow.
• Establish and maintain model monitoring and observability using tools such as Grafana or comparable platforms to proactively detect drift and degradation.
• Replace manual and rule-based processes with scalable ML-driven automation that reduces intervention and improves turnaround times.
• Translate improvements in model performance into measurable business outcomes, including operational savings, efficiency gains, and customer value.
• Collaborate closely with product, engineering, and operations stakeholders to define problems, prioritize solutions, and successfully deploy models.
• Mentor and technically guide other data scientists and engineers, helping establish strong engineering and modeling practices.
• Independently evaluate build-versus-buy decisions and make architecture and technology tradeoffs aligned with business needs.

Requirements:

• Strong foundations in machine learning, particularly regression, classification, and time-series forecasting.
• Proven experience building and deploying machine learning models that serve real production traffic rather than remaining at proof-of-concept or notebook stage.
• Practical NLP experience involving text extraction, entity recognition, LLM-based extraction, or similar applications.
• Strong programming and data skills in Python and SQL, including experience with pandas, scikit-learn, and large datasets.
• Experience with cloud and data infrastructure, particularly AWS services such as S3 and EC2, with exposure to Airflow or similar orchestration platforms.
• Experience with model monitoring, observability, and production ML operations; familiarity with Grafana or comparable tools is valuable.
• Demonstrated ability to work effectively with noisy, unstructured, or imperfect real-world data.
• Experience diagnosing production model degradation and closing the gap between offline evaluation and live performance.
• A track record of using ML to automate manual or rule-based processes and deliver measurable improvements.
• Ability to connect technical model performance with business outcomes and communicate complex concepts clearly to non-technical stakeholders.
• Strong collaboration skills and experience partnering with product, engineering, and operations teams.
• Experience mentoring or providing technical guidance to other data scientists or engineers.
• Ability to independently evaluate architecture options and make effective build-versus-buy decisions.
• Excellent written and verbal communication skills.
• Experience in logistics, supply chain, transportation, real-time streaming data such as Kafka, or production LLM/GenAI applications is a plus.

Benefits:

• Competitive compensation package with stock options.
• Medical benefits starting from the first day of employment.
• 36 days of PTO covering sick, casual, and earned leave.
• 5 additional global recharge days and 2 volunteer days.
• Home-office setup and technology reimbursement.
• Lifestyle and family benefits.
• Mental wellness support and guidance.
• Ongoing learning and professional development opportunities, including development programs and communication-focused initiatives.
• Collaborative and inclusive work environment that values diversity and continuous learning.