Senior AI Engineer

Role overview This Senior AI Engineer role delivers production agentic and AI systems on a rotating portfolio of client engagements, ranging from deep single-company transformations to portfolio-wide AI readiness programs. The engineer operates as the senior IC on a delivery pod, partnering daily with an AI Architect and an AI Transformation Consultant to ship RAG systems, agentic workflows, MCP-based integrations, and evals/observability frameworks that turn prototypes into load-tested, monitored production services.

Responsibilities - Build production-grade agentic systems on Databricks and other lakehouse platforms, including orchestration frameworks, task runners, and monitoring layers. - Implement RAG pipelines, vector stores, and retrieval architectures that hold up under real-world load, and stand up evals, observability, and guardrails for client-deployed AI. - Design and integrate MCP servers and tool-calling layers between LLMs and client systems of record, internal APIs, and third-party SaaS. - Lead the AI engineering workstream on the client pod, partnering with the Architect on platform decisions and the Consultant on roadmap. - Coach client engineering teams on production AI patterns including prompt management, model routing, and FinOps. - Contribute to internal reference architectures and scan/blueprint tooling used across the practice.

Requirements - 5+ years building production data and ML systems in Python, including 2+ years on LLM-based or agentic systems. - Hands-on experience with at least one major LLM orchestration framework such as LangChain, LangGraph, Langflow, or the Databricks Agent Framework. - Production experience with Databricks (Unity Catalog, Delta Live Tables, MLflow) or comparable lakehouse platforms such as Snowflake with dbt. - Deep knowledge of RAG architectures, vector databases, and embedding pipelines. - Proven track record taking AI systems from prototype to production, including evals, monitoring, and on-call ownership. - Comfort working directly with client engineering teams as a peer and a coach.

Nice to have - Databricks, AWS, or Azure certifications; experience with MCP, tool-calling protocols, or agentic protocol design. - Background in security-aware AI engineering, multimodal AI across text, document, and image, and FinOps experience optimizing model and compute spend.

Benefits and work setup - Competitive compensation with performance bonuses, professional development budget, and certification support. - Direct access to Databricks, AWS, GCP, and Azure stacks, a builder culture that ships, and a flexible remote work environment.