We are looking for an AI/ML Engineer with solid experience in ETL, Databricks, and RAG (Retrieval-Augmented Generation) to build and deploy AI/ML and data solutions.
Key Responsibilities
- Develop and maintain ETL/ELT data pipelines using Databricks.
- Build and implement RAG-based AI applications.
- Work with LLMs, embeddings, vector databases, and prompt engineering.
- Prepare, clean, transform, and validate data for AI/ML applications.
- Develop ML/AI solutions using Python.
- Integrate AI models with enterprise applications and data platforms.
- Optimize data pipelines and AI solutions for performance and scalability.
- Work with Data Engineering and business teams to deliver AI solutions.
Mandatory Skills
- Strong hands-on experience in Python.
- Strong experience with Databricks and ETL/Data Engineering.
- Hands-on experience with RAG architecture and LLM applications.
- Good knowledge of SQL and data processing.
- Experience with LLMs, embeddings, vector databases, and prompt engineering.
- Understanding of Machine Learning and AI concepts.
Good to Have
- Experience with PySpark / Spark.
- Knowledge of Azure/AWS/GCP.
- Experience with LangChain, LlamaIndex, or similar frameworks.
- Knowledge of MLflow and AI/ML model deployment.
- Experience with REST APIs and cloud-based AI services.