Key Responsibilities: /n /n Agent Development & Architecture: /n /n

- Build agentic workflows using LangChain/LangGraph and similar frameworks.
- Develop autonomous agents for data validation, reporting, document processing, and domain workflows

/n

- Deploy scalable, resilient agent pipelines with monitoring and evaluation

/n /n /n GenAI Application Engineering /n /n

- Develop GenAI applications using models like GPT, Gemini, and LLaM

/n

- Implement RAG, vector search, prompt orchestration, and model evaluation

/n

- Partner with data scientists to productionize POCs

/n /n /n Data & Platform Engineering /n /n

- Build distributed data pipelines (Python, PySpark)

/n

- Develop APIs, SDKs, and integration layers for AI-powered applications

/n

- Optimize systems for performance and scalability across cloud/hybrid environments.

/n /n /n MLOps / LLMOps /n /n

- Contribute to CI/CD workflows for AI models-deployment, testing, monitoring

/n

- Implement governance, guardrails, and reusable GenAI frameworks.

/n /n /n Collaboration & Stakeholder Engagement /n /n

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

/n

- Participate in architecture reviews and iterative development cycles

/n

- Support knowledge sharing and internal GenAI capability building.





/n /n /n Key Requirements: /n /n /n

- 8-12 years of experience in AI/ML engineering, data science, or software engineering, with atleast 2 years focused on GenAI

/n

- Strong programming expertise in Python, distributed computing using PySpark, and API development

/n

- Hands on experience with LLM frameworks (LangChain, LangGraph, Transformers, OpenAI/Vertex/Bedrock SDKs)

/n

- Experience developing AI agents, retrieval pipelines, tool calling structures, or autonomous task orchestration

/n

- Solid understanding of GenAI concepts: prompting, embeddings, RAG, evaluation metrics, hallucination identification, model selection, fine tuning, context engineering

/n

- Experience with cloud platforms (Azure/AWS/GCP), containerization (Docker), and CI/CD pipelines for ML/AI

/n

- Solid problem solving, system design thinking, and ability to translate business needs into scalable AI solutions

/n

- Excellent verbal, written communication and presentation skills. Good to Have

/n

- Experience in workflow automation and building reusable AI components

/n

- Background in analytics, statistical models, or enterprise data products

/n

- Experience with MLOps / LLMOps tooling

/n /n

📌 Data Scientist (Tiruchirappalli)
🏢 Dun u0026 Bradstreet India
📍 Tiruchirappalli