Data Scientist II

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

📋 Description

• Develop and sustain machine learning and optimization models across the quick-commerce ecosystem, focusing on supply-demand alignment, dynamic and surge pricing, recommendations, ETA forecasting, and marketplace optimization.

• Play a key role in enhancing Butler's conversational ordering AI by analyzing customer intent derived from text, voice, and images, ensuring requests are transformed into fulfillable and competitively priced orders.

• Design and conduct A/B tests and quasi-experiments related to pricing, matching, recommendations, and the Butler platform.

• Convert chaotic marketplace data into actionable insights for stakeholders.

• Extract features from order events, courier tracking, geospatial data, pricing models, and conversational inputs from text and voice.

• Manage models throughout the data pipeline lifecycle, including training, deployment, monitoring, and retraining.

• Address any model or configuration drift effectively.

• Collaborate with product managers, engineers, DevOps, operations teams, and other groups.

• Assist in diagnosing real-time issues such as pricing discrepancies and increased failure rates.

• Oversee the health of models and metrics, contributing to logging, observability, analysis, and deployment strategies.

• Identify opportunities for enhancement in measurement, modeling, and processes through gradual improvements.

⛳️ Requirements

• 3 to 4 years of relevant, non-internship experience in data science or machine learning within fast-paced startups or large tech corporations.

• Proficient in A/B testing design, power analysis, and quasi-experimental methods, including difference-in-differences, instrumental variables, synthetic control, and an understanding of interference in marketplace/network contexts.

• Strong foundation in forecasting and experience in either operations research or reinforcement learning as applied to allocation, matching, or pricing challenges.

• Proven track record of developing, selecting, and maintaining features from extensive, complex real-world datasets.

• Comfortable with deploying, monitoring, and sustaining machine learning pipelines.

• Proficient in Python and SQL.

• Capable of efficiently handling large-scale data.

• Strong problem-solving skills based on first principles and a history of delivering high-quality results while maintaining reliability, latency, and interpretability.

• A proactive approach to shipping early and iterating on projects.

• Bachelor's or Master’s degree in Computer Science, Statistics, Engineering, or a related quantitative discipline.

• Practical experience in quick commerce, marketplaces, logistics, ride-hailing, or on-demand delivery sectors.

• Familiarity with NLP/LLM, including intent classification, entity extraction, embeddings, or handling conversational/voice data.

• Comfortable with big data and streaming tools such as Spark and Kafka, along with real-time inference capabilities.

🏝️ Benefits

• An inclusive and diverse workplace.

• A remote work environment.

• Competitive compensation package.

• Potential share options for select positions.

• Ongoing training opportunities.

• Annual learning stipend.

• A high level of autonomy.

• Access to mentorship.