Lead Data Scientist

Requirements

Lead Data Scientist

5 years of experience

fraud detection, natural language processing (NLP), and predictive modeling

Python

hands-on contributor

strategic leader

Key Responsibilities

Machine Learning & AI Development

• Lead the design, development, and deployment of machine learning models for fraud detection, anomaly detection, and behavioral analytics.
• Develop NLP models for text classification, entity extraction, sentiment analysis, and conversational AI.
• Conduct feature engineering, model selection, hyperparameter tuning, and optimization to maximize performance.
• Build end-to-end ML pipelines from data preprocessing to model deployment.
  

Fraud Detection & Risk Analytics

• Apply advanced analytics and ML techniques to detect fraudulent patterns and anomalies across financial transactions, e-commerce, and other business workflows.
• Work with business teams to translate fraud detection requirements into scalable AI/ML solutions.
• Continuously monitor, test, and improve fraud detection models to minimize false positives and maximize accuracy.
  

Leadership & Collaboration

• Mentor, guide, and provide technical leadership to a team of data scientists and analysts.
• Collaborate with data engineers to build scalable data pipelines and ensure data quality for model training.
• Partner with product managers, engineers, and domain experts to align AI/ML solutions with business objectives.
• Present findings, insights, and recommendations to C-level stakeholders and business leaders.
  

Innovation & Research

• Stay updated with emerging trends in machine learning, deep learning, and NLP research.
• Drive experimentation with transformer-based architectures, generative AI, and advanced fraud detection techniques.
• Contribute to intellectual property development and thought leadership in data science.
  

Required Skills & Qualifications

• Experience: Minimum 5+ years in data science, with proven expertise in leading ML projects.
• Strong proficiency in Python and data science libraries (scikit-learn, TensorFlow, PyTorch, Pandas, NumPy, spaCy, NLTK).
• Demonstrated experience in fraud detection, anomaly detection, or risk analytics.
• Strong expertise in NLP techniques such as tokenization, embeddings, LSTMs, Transformers, and BERT/GPT-based models.
• Solid understanding of machine learning algorithms, deep learning architectures, and statistical modeling.
• Experience with big data tools (Spark, Hadoop) and working on large-scale datasets.
• Familiarity with cloud platforms (AWS, Azure, GCP) and ML services for scalable deployment.
• Proficiency in SQL, data visualization tools (Tableau, Power BI, matplotlib, seaborn).
• Strong leadership, mentoring, and cross-functional collaboration skills.
• Ability to explain technical solutions to non-technical stakeholders effectively.