Description

You will build and maintain data pipelines and AI-driven systems, focusing on LLM and RAG implementations.

Responsibilities

• Develop and deploy ETL processes to handle large datasets.
• Implement RAG and LLM workflows using transformer-based models.
• Build information retrieval systems using vector search and traditional methods.
• Design and manage data storage using SQL and NoSQL databases.
• Write clean, maintainable Python code for machine learning and data tasks.

Required Skills

• 5 years of experience in data engineering or machine learning roles.
• Proficiency in Python and version control with Git.
• Deep understanding of NLP, including tokenization, embeddings, and sequence-to-sequence models.
• Experience with transformer models such as BERT, GPT, or T5.
• Hands-on experience with PyTorch or TensorFlow.
• Knowledge of vector search techniques and frameworks like Elasticsearch or Lucene.
• Competency in TF-IDF and BM25 retrieval methods.
• Experience managing SQL and NoSQL databases.
• B Tech degree.

Preferred Skills

• Experience training large language models using supervised and unsupervised learning.

Key Skills

Education

B Tech