Senior Data Engineer

Job Title: Agentic Data Engineer Duration: 12 months + 1 month notice Day Rate: Up to $115 per hour Location: Primarily remote - Candidates must reside in the U.S. (Ideally ET time zone) Sponsorship: No Sponsorship is required A Senior Data Engineer is required to join a major international airline undergoing a significant three-year data transformation. Following a strategic review approximately a year ago that identified gaps in their current use of data and automation, the business is now executing an ambitious agentic push across data engineering, analytics, and AI-driven workflow optimisation. This is a greenfield opportunity to help shape how the organisation builds and delivers data products using modern agentic tooling, reducing traditional development lifecycle overhead, accelerating delivery, and embedding AI into every stage of the engineering process. As the Senior Data Engineer, you will work at the intersection of data engineering, software engineering, and AI-native development. Your primary objective is to compress the traditional data engineering lifecycle by embedding agentic AI tooling into how pipelines are designed, built, tested, and deployed. You will be expected to move fast, think in systems, and demonstrate what modern data delivery looks like when AI is a first-class citizen of the development workflow. Key Responsibilities • Design and build data pipelines and infrastructure on the Databricks platform, leveraging AWS or Azure cloud environments. • Develop and orchestrate multi-step agentic workflows using CLI coding agents (Claude Code, Codex, Kiro, and equivalents). • Use agentic tooling to actively accelerate and automate the data engineering development lifecycle — from spec refinement to deployment. • Implement Infrastructure as Code (IaC) to provision and manage cloud data infrastructure reliably and repeatably. • Design systems using RAG (Retrieval-Augmented Generation), vector stores, and MCP (Model Context Protocol) to give agents controlled access to tools and data sources. • Treat prompts, skills, and context templates as version-controlled, reusable engineering assets. • Run agent evaluation frameworks and monitor token usage and cost to ensure quality and efficiency. • Engage directly with the business to understand requirements and translate them into fast, high-quality data solutions. • Contribute to a culture of rapid, iterative delivery — 'squishing' the traditional development lifecycle through smart use of AI tools. Skills & Experience Essential • Strong background in data engineering with hands-on software engineering capability. • Proven experience with the Databricks platform. • Familiarity with Infrastructure as Code (IaC) tooling and practices. • Hands-on experience with AWS or Azure — building and managing cloud data infrastructure. • Demonstrable interest and exposure to agentic AI development — not just using chat assistants, but building with them. • Strong communication skills; ability to engage with the business and translate needs into technical deliverables quickly. • Comfortable working at pace in an environment that values rapid, iterative delivery. Highly Desirable • Hands-on fluency with CLI coding agents — Claude Code, OpenAI Codex, Kiro, or equivalents — as a core part of your development workflow. • Experience designing multi-step agent workflows and orchestration pipelines. • Practical knowledge of MCP (Model Context Protocol) for giving agents controlled access to tools and data sources. • Experience with RAG architectures and vector stores. • Familiarity with Amazon Bedrock — highly advantageous. • Systems thinking and design capability — able to architect as well as build. • Approach to treating prompts, agent skills, and context templates as version-controlled, reusable assets. • Experience with agent evaluation frameworks and token/cost monitoring. How to Apply To be considered for this role, please submit your CV by clicking apply.