Python Developers with ML and NLP ,4+ years experience needed, Immediate Joiners are preferred

Job Role: Python Developer with NLP and ML

Experience in years: 4+

Work Location: Kochi or Madurai

Immediate Joiners are preferred

Role Overview

We are looking for a highly skilled Python/ML/NLP Developer with approximately 4+ years of industry experience to design, develop, and deploy machine learning and natural language processing solutions. The ideal candidate will have strong hands-on experience in building ML models, working with large datasets, implementing NLP pipelines, and deploying models into production environments.

Key Responsibilities

• Design, develop, and optimize ML and NLP models for classification, clustering, information extraction, text generation, summarization, or recommendation tasks.
• Build ML models for text-cleaning, language detection, NER, document classification, or post-OCR correction.
• Develop NLP pipelines for correcting OCR errors using tokenization, embedding models (BERT, RoBERTa), and sequence models.
• Create intelligent document-understanding systems using LayoutLM/Donut/TrOCR.
• Build end-to-end NLP pipelines including preprocessing, tokenization, embedding generation, and model training.
• Experiment with traditional ML methods (SVM, Random Forest, XGBoost) and deep learning architectures (RNNs, Transformers, BERT, GPT-based models).
• Perform data exploration, feature engineering, and model evaluation using statistical and ML techniques.
• Write clean, modular, and efficient Python code for data processing, automation, model training, and API development.
• Develop reusable ML utilities, libraries, and pipelines to improve team productivity.
• Integrate ML solutions into production systems using REST APIs, microservices, or batch pipelines.
• Work with structured and unstructured data, including text, logs, and large datasets.
• Implement efficient data preprocessing, cleaning, and transformation workflows.
• Work with SQL/NoSQL databases and data tools (Pandas, NumPy, Spark optional).
• Deploy ML/NLP models into production using Docker, FastAPI/Flask/Azure, or MLOps tools .
• Monitor model performance, handle drift detection, and perform regular maintenance and retraining.