Overview
Lead client support work within the Data and Analytics Engineering practice, shaping generative AI solutions from concept to delivery across architecture, design, integration and deployment.
What you'll do
- Lead evaluation, benchmarking and implementation of scalable, secure and compliant Agentic AI frameworks aligned with enterprise business use cases and organizational strategies.
- Drive technical standardization and maturity in Generative and Agentic AI development by creating reusable orchestration blueprints, prompt engineering guides, best practices and integration patterns.
- Define scalable multi-agent system design patterns including tool usage, memory management, task routing, agent communication, human-in-the-loop processes and orchestration frameworks.
- Establish evaluation frameworks to assess Agentic AI solution performance, focusing on reasoning, tool reliability, task completion, hallucination mitigation and autonomous decision quality for production readiness.
- Design enterprise Retrieval-Augmented Generation (RAG) architectures optimizing retrieval processes, embeddings, chunking and reranking aligned with business goals and data governance.
- Mentor AI engineering teams and collaborate with stakeholders to translate objectives into AI roadmaps.
- Manage client engagements including discovery, demos, proposal development and delivery planning, leveraging DevOps, LLMOps, containerization and CI/CD pipeline expertise.
- Stay updated on Agentic AI and Generative AI advancements.
What you'll need
- Bachelor's and Master's Degree.
- 12+ years of experience in technical/technology roles.
- Oral and written proficiency in English.
Nice to have
- Proven experience with enterprise cloud AI platforms such as Azure AI Foundry (with Microsoft Fabric and Purview), Amazon Bedrock (with Knowledge Bases and Guardrails) and Google Vertex AI (with BigQuery and Agentspace) for building, governing and deploying scalable production-grade Gen AI and Agentic AI solutions.
- Hands-on expertise with leading agentic and AI orchestration frameworks such as LangGraph, CrewAI, AutoGen, Semantic Kernel or equivalents.
- In-depth knowledge of vector databases (Pinecone, Weaviate, Milvus, Azure AI Search) and their application in enterprise RAG and knowledge retrieval systems.
- Experience designing and scaling AI solutions that utilize multi-modal capabilities across text, vision, audio and document understanding.
- Familiarity with AI governance and observability platforms (e.g., LangSmith, Arize) for monitoring, tracing, debugging and compliance of production AI systems, along with expertise in selecting appropriate LLMs (GPT, Claude, Gemini, etc.) based on enterprise cost, latency and compliance requirements.
- Knowledge of AI-powered development tools (GitHub Copilot, Cursor, Windsurf) to improve engineering productivity.
Details
- Travel requirements: not specified.
Read the full description and apply on the company’s own careers page.