Data Science - Python

Total IT experience: 7 to 10 years in DWH is must

2-4 years of experience in implementing NLP/GenAI projects

1 year of experience in extract entities from Large Documents with greater than 100 pages - typically legal documents / Contract Documents /Claim Documents/medical documents

6 monthsto 1 year of experience in processing large documents using GenAI APIs like Azure OpenAI,Amazon Bedrock, Google Gemini , Anthropic Claud

Thorough understanding of NLP terminologies like Sentiment Analysis/ Entity Extraction/Topic Modeling etc

Should have used Cloud Cognitive Services for key phrase extraction and document digitization like Azure Doc Intelligence, Google Doc Intelligence, AWS Textract etc

6 months to 1 year of experience in building LLM Applications for Information Retrieval and a thorough understanding and implementation using LangChain/Vector DBs and deploying it in cloud

Shoud have understanding of GPT Architecture and open-source models like LlaMA/ Mistral etc.

Minimum 1 year of implementation experience using Classical NLP libraries like NLTK/SpaCY etc

Should be able to wtite modular code that can be productionized and well-commented coding standards and practices

Should have used advanced NLP frameworks like Keras/Transformers etc in real-time

Basic Understanding of Neural Networks for Text processing and exposure to algorithms like BERT/GPT/RNN etc

Good understanding of GenAI trends and recent model advancements

Good verbal and written communication skills

Solid understanding of REST API and frameworks like Flask and FastAPI