Position Overview:We're hiring a senior engineer to build the data foundation and the governed AI services that run on top of it. You will own pipelines from source to model in Python and dbt, ship them on Docker and Kubernetes in AWS, and expose trusted data to agents through Model Context Protocol (MCP) servers.
This is a hands-on role with broad reach. You will move between traditional data engineering and applied AI work, and partner directly with business teams to turn requests into working solutions that people rely on.
What you'll do:Data engineering- Design, build, and operate batch and incremental pipelines in Python, with dbt for transformation, testing, and documentation, and fix issues at the source.
- Containerize workloads with Docker and run them on Kubernetes, using infrastructure as code and CI/CD to ship safely and often.
- Build on AWS services for storage, compute, orchestration, and security, and tune for cost and performance.
AI and agentic engineering- Design and build MCP servers and connectors that give agents governed access to enterprise data and tools.
- Deploy and operate agentic workflows in production, including tool use, orchestration, evaluation, observability, and guardrails.
- Set patterns for authentication, access control, and auditability, and test new AI techniques so only the ones that matter reach production.
Team and business impact- Work with stakeholders to define the problem, agree on the outcome, and deliver in small, visible steps.
- Review code and mentor engineers, raising the team's standards for design, testing, and documentation.
What you'll need:- 8 or more years of professional data engineering experience, with a record of owning production systems end to end.
- Strong Python for data processing, automation, and services, plus hands-on dbt: models, tests, macros, and deployment.
- Working experience with Docker and Kubernetes to deploy, scale, and troubleshoot data workloads, with Git, CI/CD, and infrastructure as code.
- Solid AWS experience across core services for storage, compute, networking, and security.
- Advanced SQL and a sound grasp of data modeling, warehousing, and performance tuning.
- Practical knowledge of Model Context Protocol: you have built, deployed, or integrated MCP servers or similar tool interfaces for LLMs.
- Experience building or deploying agentic workflows, including orchestration, tool calling, evaluation, and monitoring, and the judgment to separate useful AI patterns from hype.
- Bachelor's degree in computer science, engineering, or a related field, or equivalent practical experience.
Nice to have:- Orchestration experience with Airflow or a comparable tool.
- Experience with a cloud data warehouse such as Redshift, Snowflake, or BigQuery.
- Familiarity with enterprise source systems such as CRM, ERP, and finance platforms, and the data quirks that come with them.
- Experience with retrieval-augmented generation, vector search, or LLM evaluation frameworks.
#LI-MT1
