Senior Architect / AI Context Engineer

Material•Los Angeles, CA

7d•$150,000 - $180,000•Hybrid

About The Position

The Senior Architect / AI Context Engineer is a strategic generalist who operates at the intersection of enterprise architecture, AI operationalization, and context engineering. This role is responsible for authoring governance artifacts, designing agent and tool-server architectures, building reusable accelerator patterns, curating agent skills and prompt harnesses, and driving the AI-native design agenda across the organization. This is the role that bridges the gap between strategic architecture decisions and hands-on AI implementation.

Requirements

8+ years in software architecture, solutions architecture, or enterprise architecture roles.
Demonstrated experience designing and building AI/LLM-integrated systems: agent architectures, prompt engineering, RAG pipelines, tool-use patterns.
Strong understanding of context engineering: structured prompt design, system prompt authoring, knowledge retrieval optimization, context window management.
Experience with at least two of: MCP (Model Context Protocol), LangChain/LangGraph, Claude API, OpenAI API, or equivalent LLM orchestration frameworks.
Proficiency in multiple programming languages (Python, TypeScript/Node.js required; others a plus).
Proven track record authoring governance artifacts: ADRs, architecture standards, SDLC documentation, security review frameworks.
Experience with enterprise platform ecosystems: Atlassian (Confluence, Jira), Azure, GitHub, Salesforce.
Strong technical writing and documentation skills; able to produce executive-ready architecture briefs and technical specifications simultaneously.

Nice To Haves

Hands-on experience with a major agentic AI ecosystem: model providers' agent runtimes, skill and tool definitions, MCP servers, and managed or hosted agent platforms.
Background in market research, consulting, or insights/analytics industries.
Experience with knowledge graph design, ontology modeling, or semantic data architectures.
Familiarity with institutional memory and knowledge management platforms, particularly internal developer tooling that exposes organizational context to AI agents.
A grounded perspective on AI adoption: recognizing that velocity bottlenecks in AI-enabled delivery are typically process habits and organizational culture rather than tooling capability.
Experience with enterprise governance models (TOGAF, Zachman, or custom tiered governance).

Responsibilities

Design, author, and maintain MCP (Model Context Protocol) server architectures across recurring patterns: knowledge and memory servers, platform API bridge servers, and event- or webhook-triggered agents, following established AI-native design principles.
Build and curate reusable agent skills, system prompts, scoring rubrics, and harness configurations for a library of governed agent archetypes.
Author and publish enterprise governance documentation: Architecture Decision Records (ADRs), security review checklists, tiered governance model documentation, and architecture review templates for the enterprise technology intake and approval pipeline.
Design and implement an enterprise context engineering layer: repo-level context file standards (AGENTS.md / CLAUDE.md conventions), templates, and harness engineering patterns.
Drive execution of a governed internal agent platform pilot: author agent archetypes, configure governed sessions with scoped tool access, and validate end-to-end audit trail flows on a managed agent runtime.
Develop and maintain an accelerator solution map: reusable toolkit pattern definitions, capability gap analysis, and accelerator specifications spanning all service lines.
Support Enterprise Knowledge Graph scoping: ontology design, data catalog foundation architecture, and schema governance, in collaboration with data science and commercial strategy teams.
Author SDLC Standards and Engineering Operating Model artifacts: quality gates, PR/review standards, Definition of Done/Ready templates, CI/CD control specifications.
Produce EA leadership artifacts: Enterprise Capability Maturity Map, Technology Demand and Decision Flow Dashboard, Application/Tool Portfolio Map, cross-lane integration maps, and an AI Readiness Scorecard.
Operate as the primary technical liaison between the enterprise architecture function and service lines teams, translating strategic architecture intent into actionable engineering guidance.