Responsibilities

• Develop models to categorize and group text data for downstream applications (e.g., recommendation systems, sentiment analysis).
• Use techniques like LDA and NMF to discover hidden themes in large text datasets.
• Implement systems for detecting outliers in text-based data, ensuring operational integrity.
• Apply statistical and machine learning methods to model temporal data trends and forecast text-related patterns (e.g., event analysis).
• Utilize advanced tools like spaCy, NLTK, BERT, and Transformers for model development and fine-tuning.
• Optimize model outputs through prompt engineering for complex tasks like summarization, translation, and question answering.
• Build, deploy, and maintain scalable NLP models using MLOps practices, ensuring smooth integration with production environments.
• Develop REST APIs for real-time model inference and set up performance metrics monitoring to track model accuracy and system performance.

Requirements

• Strong experience with Python and key data science libraries (e.g., pandas, scikit-learn, NumPy).
• In-depth knowledge of Text Classification, Clustering, and Topic Modeling techniques, as well as pre-trained models like BERT.
• Familiarity with anomaly detection algorithms and the ability to apply them in production settings.
• Experience with Time Series data and statistical modeling techniques for forecasting and trend detection.
• Experience with cloud-based tools (AWS, GCP, Azure) and MLOps for model deployment and monitoring.
• Excellent communication skills to work cross-functionally and present technical concepts to non-technical stakeholders.

Posted By