Senior Data Scientist

This is a fully remote position, open to applicants in India.

📋 Description

• Design, construct, and operationalize machine learning models for ETA/ATA predictions utilizing regression, classification, and time-series forecasting techniques.

• Create NLP/LLM-driven extraction pipelines for message-based ETA and status updates.

• Manage models comprehensively from data pipeline through training, deployment, monitoring, and retraining.

• Work with noisy, real-world data from logistics and supply chain environments.

• Identify discrepancies between offline evaluation metrics and real-time production accuracy, and implement solutions.

• Develop and sustain automated training/retraining pipelines using orchestration tools such as Airflow.

• Establish and uphold model monitoring and observability using Grafana or equivalent tools.

• Transition manual or rule-based processes to ML-driven automation.

• Convert enhancements in model performance into operational cost savings, efficiency improvements, and outcomes relevant to deals.

• Mentor and support fellow data scientists and engineers.

• Make independent decisions regarding build-vs-buy and architectural trade-offs.

⛳️ Requirements

• Solid understanding of machine learning principles across regression, classification, and time-series forecasting.

• Experience in NLP — including text extraction, entity recognition, or LLM-based extraction.

• Proven production ML experience — you have deployed models that serve real traffic, not just developed POCs or notebooks.

• Strong proficiency in Python and SQL — including pandas, scikit-learn, and the ability to query large datasets (experience with Redshift/Snowflake is a plus).

• Familiarity with cloud and data infrastructure — AWS (S3, EC2), and orchestration tools like Airflow for managing training/retraining pipelines.

• Experience in setting up or utilizing model monitoring and observability tools (Grafana or similar).

• Comfortable handling noisy, real-world data instead of clean, curated datasets.

• Proven ability to diagnose and address discrepancies between offline evaluation outcomes and live production performance.

• A history of replacing manual/rule-based processes with machine learning solutions.

• Capability to translate model outputs into business value and effectively communicate that impact to non-technical stakeholders.

• Experience in cross-functional collaboration with product, engineering, and operations teams.

• Background in mentoring or guiding other data scientists or engineers.

• Ability to independently make build-vs-buy and architectural trade-offs.

• Proven track record of minimizing manual intervention or turnaround time through automation.

• Excellent verbal and written communication skills.

• Educational background is optional.

• Experience in logistics, supply chain, or transportation is a plus.

• Familiarity with real-time/streaming data (e.g., Kafka) is advantageous.

• Exposure to LLM/GenAI applications in production is beneficial.

🏝️ Benefits

• Competitive compensation package including stock options.

• 5 global recharge days.

• Generous paid time off (PTO) and standard holidays.

• Parental leave provided for all parents.

• Annual wellness stipend.

• Volunteer days available.

• Medical benefits commence on the first day of employment.

• 36 PTO days (including Sick, Casual, and Earned), alongside 5 recharge days and 2 volunteer days.

• Home office setup assistance and technology reimbursement.

• Lifestyle and family benefits offered.

• Mental wellness support and resources provided.

• Continuous learning and development opportunities, including a professional development program and Toastmasters club.