Dnb3mo ago

Analyst II - Data Science (R-18850)

ChennaiEmployee: Full Timemid

Data ScienceData & AI

0 views0 saves0 applied

Apply Now

Quick Summary

Overview

Shape the Future with Dun & Bradstreet At Dun & Bradstreet, we believe data has the power to create a better tomorrow. As a global leader in business decisioning data and analytics, we help companies worldwide grow, manage risk, and innovate.

Technical Tools

azuredockergcplangchainopenaipythonsparkci-cdrest-apis

Shape the Future with Dun & Bradstreet

At Dun & Bradstreet, we believe data has the power to create a better tomorrow. As a global leader in business decisioning data and analytics, we help companies worldwide grow, manage risk, and innovate. For over 180 years, businesses have trusted us to turn uncertainty into opportunity. We’re a diverse, global team that values creativity, collaboration, and bold ideas. Are you ready to make an impact and help shape what’s next? Join us! Explore opportunities at dnb.com/careers.

We are looking for an experienced AI Engineer to design, build, and operationalize AI driven solutions for our global Analytics organization. The ideal candidate will have strong hands-on expertise in Python, PySpark, agentic workflow development, and modern GenAI frameworks, with experience building scalable applications using LLMs, retrieval systems, and automation pipelines. You will work closely with data scientists, MLOps engineers, and business stakeholders to build intelligent, production grade systems that power next generation analytics and decisioning capabilities,aligned with the organization’s GenAI roadmap.

Develop AI Agents: Design, code, and implement AI agents and copilots using Google's Gemini API and Microsoft Copilot Studio.

Integrate Systems: Write robust Python code to connect AI agents with enterprise data sources, internal tools, and third-party services via REST APIs.

Implement RAG Patterns: Build and refine Retrieval-Augmented Generation (RAG) pipelines to ensure agents provide accurate, context-aware responses grounded in proprietary data.

Prompt Engineering: Craft, test, and iterate on effective prompts to guide agent behavior, ensuring reliability, safety, and desired outcomes.

Full Lifecycle Development: Participate in the entire development lifecycle, from initial concept and design through to testing, deployment, and maintenance.

Collaboration: Work closely with senior engineers to overcome technical challenges and with product managers to translate business requirements into functional agent capabilities.

Troubleshooting: Debug and resolve issues in agent performance, whether they stem from the underlying LLM, the data pipeline, or the integration code.

Work with analytics, product, and engineering teams to define and deliver AI solutions.

Participate in architecture reviews and iterative development cycles.

Support knowledge sharing and internal GenAI capability building.

Bachelor's degree in computer science, Software Engineering, or a related field.

5+ years of professional software development experience.

Strong programming proficiency in Python and a solid understanding of object-oriented principles.

At least 1 year of hands-on experience building applications with Large Language Models (LLMs) through professional work, significant personal projects, or open-source contributions.

Solid understanding of core LLM concepts, including prompt engineering, embeddings, and function calling/tool use.

Experience consuming and interacting with REST APIs.

A proactive, problem-solving mindset and a strong desire to learn and adapt in a fast-evolving field.

Direct experience making API calls to Google's Gemini, OpenAI models, or using Microsoft Copilot Studio/Azure OpenAI Service.

Familiarity with agentic frameworks like LangChain, LlamaIndex, or Microsoft's Semantic Kernel.

Experience with cloud services on GCP (like Vertex AI) or Azure.

Knowledge of vector databases (e.g., Pinecone, Chroma, Weaviate) and how they fit into RAG architectures.

Basic understanding of CI/CD pipelines and containerization (Docker).