Data Engineer

Nextwebi; Bengaluru; On-site; INR 900,000 - 1,300,000; Full time

Job summary

Nextwebi is seeking a Data Engineer with strong expertise in SQL, Python, and Retrieval-Augmented Generation (RAG) to build production-ready AI solutions. The role focuses on developing, enhancing, and scaling enterprise AI applications using LLMs and related technologies.

You will work on data extraction, transformation, and analysis for both structured and unstructured data, and develop conversational AI capabilities for natural language querying of business data.

Qualifications

• Proficient in Python and SQL for data extraction, transformation and analysis.
• Hands-on experience building RAG-based AI applications.
• Experience with LLMs, vector databases, embeddings and document processing.
• Strong analytical and problem-solving abilities.

Responsibilities

• Develop and enhance RAG-based AI applications using Python and SQL.
• Perform data extraction, transformation, and analysis on structured and unstructured data.
• Build conversational AI solutions enabling natural language querying of business data.
• Improve AI-powered document analysis tools including data ingestion, retrieval, and output.
• Work with document processing, embeddings, vector databases, and LLM integrations.
• Collaborate with cross-functional teams to deliver scalable AI solutions.

Skills

Python

SQL

RAG-based AI

LLMs

vector databases

embeddings

document processing

AI application development

analytical thinking

Tools

Tableau

Vector databases

Embeddings

Document processing tools

Job description

We are seeking a Data Engineer with strong expertise in SQL, Python, and Retrieval-Augmented Generation (RAG) application development. The ideal candidate should have hands‑on experience building production‑ready AI solutions using Large Language Models (LLMs) and be capable of developing, enhancing, and scaling enterprise AI applications.

Key Responsibilities

• Develop and enhance RAG-based AI applications using Python and SQL.
• Perform data extraction, transformation, and analysis on structured and unstructured data.
• Build conversational AI solutions that enable natural language querying of business data.
• Enhance AI-powered document analysis tools by improving data ingestion, retrieval, and output capabilities.
• Work with document processing, embeddings, vector databases, and LLM integrations.
• Collaborate with cross‑functional teams to deliver scalable AI solutions.

Experience

1. Conversational Data Quality: A natural language interface over clinical milestone data (Excel inputs + rules) where a study manager can ask open‑ended questions like "show me rule violations for sites in Spain." The point is moving beyond rigid tabular tools to a context‑aware, question‑driven experience.

2. ICF Analysis Tool: Already in production. Ingests "Informed Consent Form: documents from a folder, runs them through an AI engine that flags suspicious data‑sharing language, surfaces offending paragraphs, allows user overrides, and exports to Excel." The hire needs to own, improve, and expand this kind of tooling.

Required Skills

• Strong proficiency in Python and SQL (data extraction, transformation, and analysis).
• Hands‑on experience building RAG-based AI applications (mandatory).
• Experience with LLMs, vector databases, document processing, embeddings, and AI application development.
• Strong analytical and problem‑solving skills.

Good to Have

• Tableau (basic dashboard/report development is sufficient).
• Experience in the Life Sciences