Data Engineer-Python and GenAI Developer

Role Overview:

We are looking for a Python Developer (ETL & GenAI Pipelines) to design, build, and optimize data workflows and AI-powered applications. The role is primarily focused on Python-based ETL and transformation pipelines, with intermediate-level exposure to Generative AI (LLMs, prompt engineering, RAG) for enhancing automation and intelligence in data processes.

Key Responsibilities:

- Design and implement robust ETL pipelines for structured and unstructured data.

- Develop Python scripts for data cleaning, transformation, and enrichment.

- Integrate pipelines with databases, APIs, and cloud storage.

- Build Python-based pipelines that leverage LLMs for text processing, summarization, and enrichment.

- Implement retrieval-augmented generation (RAG) workflows with vector databases.

- Document pipeline architecture, workflows, and best practices.

Key Qualifications:

- 3-5 years of strong proficiency in Python (OOP, data structures, Pandas, NumPy, PySpark).

- Familiarity with APIs, microservices, and cloud-native development.

- Hands-on experience with LLM frameworks (Hugging Face, LangChain, OpenAI API).

- Basic prompt engineering and fine-tuning skills.