Lead, AI Engineer

Blend is a premier AI services provider, committed to co-creating meaningful impact for its clients through the power of data science, AI, technology, and people. With a mission to fuel bold visions, Blend tackles significant challenges by seamlessly aligning human expertise with artificial intelligence. The company is dedicated to unlocking value and fostering innovation for its clients by harnessing world-class people and data-driven strategy. We believe that the power of people and AI can have a meaningful impact on your world, creating more fulfilling work and projects for our people and clients. For more information, visit www.blend360.com 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.

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 fast-moving agentic AI ecosystem and proactively bring in relevant tools, frameworks, and techniques.

Atleast 4 years of overall AI/ML experience out if which at least 2 years of Generative AI solutions. Strong background in applied ML, data science, LLM and Agentic AI Engineering Systems with demonstrated delivery and client facing experience. Deep expertise in evaluation design, metrics, and dataset curation for LLM systems. Proven experience in model selection and prompt engineering, including structured output and tool-use prompting. Strong proficiency in Python and major ML frameworks (PyTorch, TensorFlow, Scikit-learn). Strong experience in LLM fine-tuning, RAG Context Engineering, Claude Code, Open AI Codex, Agentic Workflows. Strong RAG design choices (chunking, embeddings, retrieval strategies, reranking) and how to evaluate them. Must have implemented Agentic AI SDLC Working with GenAI on Azure, AWS, or Snowflake involves leveraging cloud-native AI tools—such as Azure OpenAI, AWS Bedrock, or Snowflake Cortex—to build or