WEX is a leading company in the financial technology sector, and they are seeking a Sr. Staff AI Engineer specializing in Context Engineering. The role focuses on designing and building high-performance software systems for enterprise AI workflows, particularly in the areas of distributed systems and cloud-native architecture.
Responsibilities:
- Define and own the 3–5 year technical roadmap for our high-scale, AI-ready Data Lakehouse
- Prototype and benchmark emerging trends in the AI ecosystem
- Set the gold standard for code quality, CI/CD, and system design across the organization
- Design the platform-level interfaces required for Agentic workflows
- Build the 'Context Fabric' that allows AI agents to securely discover, access, and interpret enterprise data
- Implement and advocate for emerging standards like the Model Context Protocol (MCP) to ensure interoperability
Requirements:
- 15+ years in software engineering
- Expert in Java or Scala (distributed systems focus) and Python
- Deep experience building extensible frameworks, high-throughput APIs, and libraries used by other developers
- Hands-on experience with the latest trends in agent development, such as Multi-Agent Orchestration (using frameworks like LangGraph or CrewAI) and the transition from static RAG to Agentic RAG
- Knowledge of the Model Context Protocol (MCP) and other emerging standards that allow AI agents to interact with diverse data sources and tools in a plug-and-play manner
- Experience building 'AI-native' CI/CD features, such as automated LLM-based evaluations (evaluating agent reasoning paths in the build pipeline) and Automated Root-Cause Analysis for system failures
- Understanding of how to build automated workflows that pause agent actions for human approval, ensuring safety and governance for autonomous systems
- Expert-level experience with GitOps workflows (e.g., ArgoCD or Flux) to ensure that all platform configurations—including AI prompt templates and model parameters—are versioned, audited, and automatically reconciled
- Mastery of Terraform
- Proficiency in designing complex pipelines (e.g., GitHub Actions, GitLab CI) that integrate automated testing, security scanning, and deployment gates for high-availability systems
- Experience with OpenTelemetry (OTel) to build deep visibility into distributed systems
- Deep proficiency in navigating and configuring the AWS and Azure Management Consoles
- Proven ability to build platform layers that bridge AWS and Azure, allowing for seamless deployment and management across a multi-cloud environment
- Experience using cloud-native tools (AWS CloudWatch, Azure Monitor, Cost Explorer) to manage platform health, security posture, and spend at an enterprise scale
- A proven track record of 'leading by influence'—driving adoption of new technologies across multiple autonomous teams
- Ability to communicate complex architectural trade-offs (e.g., 'Latency vs. Consistency') to both C-suite executives and engineers
- Bachelor's or Master's degree in Computer Science (Distributed Systems focus) preferred, or equivalent deep industry experience