Sr Staff AI Engineer, Context Engineering

WEX•California, IL

20h•$220,000 - $255,800

About The Position

As a Sr. Staff AI Platform Engineer, you are first and foremost a Systems Architect. Your mission is to design and build the high-performance software foundation that powers the enterprise. While your core expertise lies in distributed systems, cloud-native architecture, and platform engineering, you will apply these skills specifically to the "Context Layer"—the specialized infrastructure required to fuel next-generation Agentic AI workflows. You will operate at the intersection of Systems Programming and Modern AI Infrastructure, solving "hard-tech" problems like real-time data orchestration, automated metadata evolution, and multi-cloud compute optimization. This is a "platform-as-a-product" role; you build the tools, SDKs, and engines that enable hundreds of other engineers to build autonomous agents with ease. The role also involves designing platform-level interfaces required for Agentic workflows, focusing on standardized "Host-to-Server" communication and tool-execution environments. This includes building robust "Human-in-the-Loop" (HITL) triggers and fail-safe mechanisms for autonomous actions. You will build the "Context Fabric" that allows AI agents to securely discover, access, and interpret enterprise data, architecting systems that move beyond basic search into Reasoning-based Retrieval, where the platform understands the intent behind an agent's query. Additionally, you will implement and advocate for emerging standards like the Model Context Protocol (MCP) to ensure interoperability, and stay ahead of trends such as Small Language Models (SLMs) for edge-compute and Agentic RAG, ensuring the platform can pivot as the industry evolves.

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.
Prioritize building "software-defined infrastructure" over manual configuration.
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 (Human-in-the-Loop (HITL)).
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, focusing on tracking both system performance and business-centric AI metrics.
Deep proficiency in navigating and configuring the AWS and Azure Management Consoles.
Comprehensive understanding of how to architect, secure, and optimize core services (IAM, EC2/VMs, S3/Blob, and specialized AI/ML service suites) natively within both ecosystems.
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.
Equivalent deep industry experience.

Nice To Haves

Bachelor’s or Master’s degree in Computer Science (Distributed Systems focus).

Responsibilities

Define and own the 3–5 year technical roadmap for our high-scale, AI-ready Data Lakehouse, optimized for AI Agent operations and efficient context retrieval, delivering low-latency, high-throughput data access essential for vector databases and LLM-driven applications.
Prototype and benchmark emerging trends in the AI ecosystem, evaluating next-generation architectural patterns such as Multi-Agent Orchestration, autonomous long-term memory management, and specialized Agent Evaluation frameworks.
Set the gold standard for code quality, CI/CD, and system design across the organization, leading cross-functional architecture reviews and serving as the final escalation point for complex technical bottlenecks.
Design the platform-level interfaces required for Agentic workflows, focusing on standardized "Host-to-Server" communication and tool-execution environments, including building robust "Human-in-the-Loop" (HITL) triggers and fail-safe mechanisms for autonomous actions.
Build the "Context Fabric" that allows AI agents to securely discover, access, and interpret enterprise data, architecting systems that move beyond basic search into Reasoning-based Retrieval.
Implement and advocate for emerging standards like the Model Context Protocol (MCP) to ensure interoperability, and stay ahead of trends such as Small Language Models (SLMs) for edge-compute and Agentic RAG.