Data Science

Description

Job Summary: The Data Science professional at KarHub will develop intelligent systems combining GenAI and Machine Learning to solve strategic problems in sales, customer experience, and operational efficiency. Key Highlights: 1. Building and evolving intelligent systems with GenAI and ML 2. ML and GenAI models for sales, marketing, pricing, and customers 3. Collaborating with Data Engineering to deliver scalable solutions **Description and Responsibilities:** **Working Hours:** 9:00 AM to 6:00 PM **Level:** Professional **Employment Type:** Service Provider (PJ) **About:** As a Data Scientist at KarHub, you will contribute to building and evolving intelligent systems that combine GenAI and traditional Machine Learning models to solve real-world, high-impact problems across three strategic pillars: sales, customer experience, and operational efficiency. **Responsibilities:** Design, develop, and evolve Machine Learning and GenAI models supporting areas such as sales, marketing, catalog, pricing, and customer experience. Conduct exploratory analyses, prepare data, engineer features, and build ML pipelines that generate actionable recommendations and insights. Design and optimize prompts, create classifiers and LLM-based agents to accelerate internal operations and improve the customer journey. Participate in the evolution of existing models, ensuring robustness, monitoring, scalability, and production performance. Build impact analyses and identify opportunities to optimize campaigns, dynamic pricing, cross-selling, prioritization of owned inventory, and logistics strategies (e.g., fulfillment shipping). Collaborate with Data Engineering and business teams to transform strategic problems into intelligent, scalable solutions—always responsibly and with impact focus. **Requirements:** **What We’re Looking For:** Bachelor’s degree in Data Science, Statistics, Mathematics, Computer Science, Engineering, or related fields. Proficiency in Python and SQL for large-scale data manipulation, analysis, and modeling. Practical knowledge of Machine Learning (regression, classification, decision trees, clustering, time series, etc.) and familiarity with Scikit-learn. Knowledge of RAG, embeddings, and prompt engineering. Experience with vector databases (Pinecone or similar). Ability to communicate results clearly, visually, and impact-oriented. **Nice-to-Haves:** Practical experience deploying models into production, managing pipelines, monitoring, or using tools like Airflow/DBT. Experience with GCP and distributed environments (Spark/PySpark). Familiarity with TensorFlow, PyTorch, or more advanced NLP/LLM models. **Benefits:** Health insurance