Information TechnologyFull-TimeEntry-level(0-1 yr)
Job Description
The AI Platform Engineer serves as the primary technical administrator across the International Rescue Committee's enterprise AI environments, currently including Anthropic (Claude) and OpenAI platform deployments. This role is responsible for administering AI systems, managing API keys, optimizing resources, building integrations, and collaborating with Security and engineering teams.
Major Responsibilities
AI Systems Administration & Operations (40%)
Serve as primary technical administrator across IRC enterprise AI environments, currently including Anthropic (Claude) and OpenAI platform deployments.
Manage user access, API key governance, workspace configurations, and environment-level settings across AI platforms.
Monitor system health, usage patterns, and API performance across AI tools; triage and resolve operational issues as they arise.
Maintain and improve observability across AI systems, tracking uptime, error rates, token consumption, and integration reliability.
Oversee and document configuration changes, environment updates, and deployment procedures across managed platforms.
Support responsible use by flagging anomalous usage patterns and coordinating with InfoSec on policy adherence and access controls.
Integrations & Technical Implementation (35%)
Coordinate with the DevOps, SW Engineering and Data Engineering team(s) on deployment processes, environment access, and infrastructure dependencies required to build and maintain AI integrations.
Follow established change management procedures for all configuration changes, environment updates, and integration deployments, including documentation, testing, and appropriate approvals before pushing to production.
Develop lightweight scripts, connectors, and automations to support AI-assisted workflows across teams, primarily in Python and/or JavaScript/TypeScript.
Troubleshoot integration failures, data flow issues, and API connectivity problems across the AI ecosystem.
Collaborate with the data engineering team on AI/KM pipeline work, including vector store ingestion, retrieval configuration, and source data connections.
Contribute to technical design discussions with engineering partners, translating operational requirements into implementable solutions.
Maintain technical documentation for all integrations, including architecture notes, runbooks, and dependency maps.
Track and report on AI resource utilization across platforms, identifying opportunities to reduce waste and improve cost efficiency.
Serve as the technical point of contact with the InfoSec team on matters related to AI system security, data handling, access controls, and compliance requirements.
Support risk assessments and security reviews for new AI tools or integrations by providing accurate technical context on system behavior and data flows.
Contribute to the development of technical SOPs and best-practice guidelines for AI system use, in coordination with the AI Platform Support Director and relevant stakeholders.
Stakeholder Support & Collaboration (10%)
Act as a technical resource for program and operations teams adopting AI tools, including answering implementation questions, supporting troubleshooting, and identifying configuration solutions.
Participate in rollout planning for new AI capabilities, providing grounded input on technical feasibility, integration requirements, and operational readiness.
Collaborate with the AI Platform Support Director on onboarding documentation and technical guidance materials for end users.
Contribute to sprint and project planning with accurate estimates on technical effort and dependencies.
Required Experience & Skills
AI & Cloud Platforms
Hands-on experience administering enterprise AI platforms (Anthropic, OpenAI, Azure OpenAI, or comparable tools), including API management, access controls, and environment configuration.
Familiarity with LLM application infrastructure: prompt pipelines, Model Context Protocol (MCP), other tool-calling integration frameworks, vector databases, retrieval-augmented generation (RAG) patterns, and embedding workflows.
Experience working with Databricks or comparable data/ML platforms is a strong plus.
Integration & Development
Proficiency in Python and/or JavaScript for scripting, automation, and lightweight integration work.
Experience building and maintaining REST API integrations, including authentication patterns, webhook handling, and error management.
Comfort reading and working within existing codebases without requiring significant architectural guidance.
Familiarity with version control (Git) and standard deployment practices for scripts and integrations.
Systems Administration & Monitoring
Experience monitoring distributed systems or SaaS platforms, including setting up alerting, reviewing logs, and diagnosing performance or availability issues.
Familiarity with usage/cost monitoring for cloud or API-based services.
Comfort operating in live production environments where reliability and data integrity are critical.
Security & Compliance
Working knowledge of information security principles as they apply to SaaS and API-based systems: access controls, credential management, data handling, and audit logging.
Ability to engage constructively with InfoSec teams, providing clear technical context to support reviews and risk assessments.
Collaboration & Communication
Ability to communicate technical concepts clearly to non-technical colleagues and program staff.
Experience contributing to cross-functional teams alongside product, engineering, and operations stakeholders.
Strong documentation habits: runbooks, SOPs, architecture notes, and internal guides.
How to Apply
Interested and qualified candidates should apply online by visiting the official application link: Apply on International Rescue Committee Portal which redirects to their Workday jobs page. Ensure you submit your application through the portal.
