Enterprise AI Systems Engineer

Juul Labs•Dallas, TX

1d•Remote

About The Position

Juul Labs is seeking an Enterprise AI Systems Engineer to own and administer enterprise AI platforms, including Claude, Gemini, OpenRouter, Cursor, and NotebookLM. This role involves managing user provisioning, security settings, and tenant configurations. The engineer will be responsible for building and maintaining essential platform content such as skills, prompts, projects, and connectors, along with their documentation. A key aspect of the role is driving user adoption, tracking consumption and spend, and reporting on usage to support business-unit chargebacks. The position also requires ensuring platform availability through monitoring, feature rollouts, and user issue triage, with ownership of escalations when issues arise. Additionally, the engineer will build and operate MCP servers and gateways for internal system integration, ensuring least-privilege access and full audit logging. A central LLM gateway will be managed for routing, authentication, rate limiting, logging, and policy enforcement across various model providers. The role involves selecting appropriate models (commercial or open-weight) based on cost, latency, capability, and data sensitivity. Building agentic workflows and automations against internal APIs and tools, with robust evaluation and guardrails, is also a core responsibility. The engineer will architect and run AI workloads on AWS and GCP, managing compute, networking, IAM, secrets management, private connectivity, Bedrock, and Vertex AI. Ownership of code in GitHub, primarily in Python and TypeScript, including branch protection, access control, secret scanning, and Actions pipelines, is expected. The role requires instrumenting the stack for cost, performance, and security telemetry, and building associated reporting for leadership and finance. Collaboration with Cybersecurity and AI Governance teams to enforce data handling, retention, and access policies, and to document standards and runbooks, is also part of the job.

Requirements

5+ years in software, cloud, or platform engineering, including recent hands-on work building and running LLM-based systems.
Experience administering an enterprise SaaS or AI tenant at scale: access management, configuration, cost control, and adoption.
Working knowledge of both commercial and open-weight LLMs, including prompt engineering, evaluation, retrieval, and agentic patterns.
Hands-on experience with Model Context Protocol (MCP), MCP gateways, or LLM gateways. Comparable API integration and middleware experience counts.
Experience with AWS and GCP architecture, including IAM, networking, secrets management, and managed AI services.
Proficiency with GitHub and standard engineering discipline: version control, code review, testing, CI/CD, and infrastructure as code.
Strong Python and/or JavaScript/TypeScript skills for building integrations, automations, and internal tooling.
Understanding of security and data governance fundamentals applied to AI work: least privilege, data classification, DLP, and auditability.
Ability to explain technical work to executives, finance, and non-technical audiences.

Nice To Haves

Vertex AI or Amazon Bedrock experience.
Self-hosted open-weight model deployment experience.
Experience with vector databases and RAG pipelines.
Experience with Splunk or another SIEM.
Cloud cost management experience.

Responsibilities

Administer enterprise Claude, Gemini, OpenRouter, Cursor and NotebookLM tenants, including user provisioning, groups and roles, workspace configuration, and tenant security settings.
Build and maintain content for AI platforms: skills, prompts, projects, connectors, and documentation.
Drive adoption of AI platforms across the company.
Track consumption and spend across all AI platforms, reporting on usage and identifying idle seats for business-unit chargeback.
Ensure platform availability through monitoring, feature rollouts, user issue triage, and escalation ownership.
Build and operate MCP servers and gateways to connect AI platforms to internal systems with least-privilege access and full audit logging.
Run the LLM gateway for centralized routing, authentication, rate limiting, logging, and policy enforcement across model providers.
Select appropriate AI models based on cost, latency, capability, and data sensitivity.
Build agentic workflows and automations against internal APIs and tools, with evaluation and guardrails.
Architect and run AI workloads on AWS and GCP, including compute, networking, IAM, secrets management, private connectivity, Bedrock, and Vertex AI.
Own and write code in GitHub (primarily Python and TypeScript), managing branch protection, access control, secret scanning, and CI/CD pipelines.
Instrument the stack for cost, performance, and security telemetry, and build reporting for leadership and finance.
Enforce data handling, retention, and access policy in collaboration with Cybersecurity and AI Governance, and write associated runbooks and standards.
Perform related duties as assigned within the scope of practice.