Job Description

We're looking for a Senior AI Data Scientist to design, build, and operationalize agentic AI systems for our customers marketing analytics practice. This is a hands-on engineering role focused on building production-grade LLM agents, tools, and pipelines — not a research or architecture-strategy role. You'll work as a data scientist to turn LLM/agentic capabilities into deployed, monitored, and reliable systems.

Key Responsibilities:

- Design and build agentic AI systems — multi-step, tool-using agents that automate marketing analytics workflows (segmentation narratives, campaign insight generation, reporting, data QA).
- Develop and deploy Claude Skills, custom tools, and function-calling workflows to extend agent capabilities within defined guardrails.
- Build and maintain Retrieval-Augmented Generation (RAG) pipelines — chunking, embedding, vector store design, retrieval tuning, and grounding strategies for internal marketing/media data.
- Implement LLM-as-judge and other automated evaluation frameworks to score agent/model outputs for accuracy, hallucination, and consistency at scale.
- Own LLMOps/AIOps practices: prompt versioning, model/version rollout strategy, cost and latency monitoring,



output drift detection, and automated regression testing for LLM pipelines.
- Apply MLOps discipline to AI systems — CI/CD for ML/LLM pipelines, containerization (Docker/Kubernetes), experiment tracking (MLflow, W&B;), and reproducible deployment across cloud platforms (AWS, GCP, Azure).
- Integrate LLM APIs (Anthropic Claude, OpenAI) into production pipelines, including structured output handling, function/tool calling, and multi-agent orchestration.
- Build evaluation harnesses and guardrails for agentic systems — output validation, safety checks, fallback logic, and human-in-the-loop review points.
- Write clean, production-quality Python and SQL to support data extraction, pipeline development, and agent tooling.
- Collaborate with data scientists to embed agentic/LLM components into existing marketing mix, segmentation, and targeting workflows.
- Document architecture, prompt design decisions, and evaluation methodology for reproducibility and team knowledge-sharing.
- Stay current with the quick-moving agentic AI ecosystem and proactively bring in relevant tools, frameworks, and techniques.

📌 Senior Data Scientist - AI Engineering (Hyderabad)
🏢 Blend360
📍 Hyderabad