AI Platform and Applications Engineer
hace 2 días
Washington
Job Description Grade Level: Grade Level 6 - Exempt Reports to: Chief Digital Officer About NED The National Endowment for Democracy supports freedom around the world. At NED, we deliver on the belief that freedom is a universal aspiration. Headquartered in Washington, DC, NED is a private, nonprofit foundation, mandated by Congress, dedicated to strengthening democratic institutions worldwide. NED reflects an enduring American commitment to stand with those striving for dignity, justice, and opportunity. In 2025, NED made 1,552 grants totaling $271 million to support the work of nongovernmental organizations advancing democratic goals in more than 90 countries, including some of the world’s most challenging and repressive environments. We seek talented, entrepreneurial professionals motivated by purpose and committed to excellence. At NED, you will join a dynamic team of experts who bring their skills, curiosity, and judgment to a consequential mission at a critical moment for democracy around the world. Our work is guided by our shared values: excellence, respect, empathy, accountability, and adaptability. Position Summary The AI Platform and Applications Engineer designs, builds, deploys, and supports secure AI-powered applications and core platform services in NED’s local-first AI environment. This role focuses on translating approved business use cases into reliable internal tools and workflows, while also maintaining the application-layer components needed to run those solutions effectively. The position combines hands-on software engineering with practical platform stewardship, including: • Model access and routing, • Retrieval pipelines, • Application integration, • Testing, • Monitoring The ideal candidate is a strong builder-operator who can: • Deliver useful AI applications, • Improve platform reliability, • Translate approved organizational needs into practical AI-enabled applications, copilots, automations, and APIs with clear success criteria, • Design, develop, test, and maintain internal AI applications that integrate with approved systems, documents, and knowledge sources, • Build user-facing and system-facing components, including APIs, lightweight interfaces, workflow integrations, and background services, • Develop retrieval-augmented generation (RAG), agentic, and related patterns for enterprise search, question answering, summarization, extraction, and other approved use cases, • Use tool calling, structured outputs, and workflow orchestration where they improve reliability, traceability, and user outcomesAI Platform Engineering and Operations, • Administer and improve core AI application platform components in NED’s local secure AI environment, including model endpoints, inference routing, embeddings services, retrieval services, and supporting application runtimes, • Configure and maintain development, test, and production deployment pipelines for AI applications using modern engineering practices, • Manage packaging, containerization, release processes, version control, and environment promotion for platform services and applications, • Support platform observability through logging, metrics, tracing, dashboards, and routine health checks, • Monitor application and platform performance, troubleshoot issues, and optimize reliability, latency, and costData Integration and Retrieval Services, • Build and maintain ingestion and retrieval pipelines for approved internal content sources, • Implement document processing, parsing, chunking, metadata enrichment, embeddings, indexing, and ranking strategies to improve answer quality and search performance, • Maintain vector stores, document stores, and related retrieval components used by AI applications, • Improve content freshness, retrieval relevance, grounding, and output consistency through testing and tuningQuality, Evaluation, and Operational Readiness, • Establish and maintain testing practices for AI applications, including unit, integration, regression, and offline evaluation workflows, • Define and track measures such as answer quality, groundedness, latency, reliability, adoption, and operational performance, • Support incident triage, issue resolution, root-cause analysis, and service improvement for AI applications in production, • Create and maintain technical documentation, runbooks, architecture diagrams, and support proceduresCross-Functional Partnership and Enablement, • Partner with business teams to identify, prioritize, prototype, and productionize high-value AI use cases, • Collaborate with IT and other internal stakeholders on hosting, access, identity, network, security, governance, and enterprise architecture requirements, • Contribute technical input to decisions involving tools, platforms, and service providers that support AI delivery, • Help develop internal guidance, usage patterns, training materials, and adoption support for AI-enabled tools and workflows QualificationsRequired, • Bachelor’s degree in Computer Science, Information Systems, Engineering, or a related field, or equivalent professional experience, • 8–10 years of experience in software engineering, platform engineering, solutions engineering, or a related technical field, • At least 2–3 years of hands-on experience building applications with modern AI/LLM technologies, • Strong programming skills in Python and/or TypeScript/Node.js, • Experience building and maintaining APIs, backend services, and production-grade integrations, • Experience developing AI-enabled applications using LLMs, embeddings, retrieval patterns, and structured outputs, • Hands-on experience with RAG pipelines and agentic workflows including document processing, chunking, embeddings, vector search, relevance tuning, and grounding strategies, • Experience with model access layers or inference runtimes such as vLLM, TGI, llama.cpp, Hugging Face Transformers, or similar tools, • Familiarity with containerized deployment and modern engineering operations, including Git, Docker, CI/CD, and application monitoring, • Experience operating and supporting technical services in a Linux-based environment, • Working knowledge of application observability, performance tuning, troubleshooting, and production support, • Experience writing technical documentation and communicating effectively with both technical and non-technical stakeholders, • Ability to work collaboratively in a mission-driven environment and translate ambiguous needs into practical solutionsPreferred, • Experience working in local, on-premises, private cloud, or otherwise restricted computing environments, • Familiarity with Kubernetes or similar orchestration platforms, • Experience with enterprise search, OpenSearch/Elasticsearch, vector databases, or other retrieval infrastructure, • Familiarity with frontend frameworks for lightweight internal tools and dashboards, • Exposure to evaluation frameworks, red-teaming approaches, or quality measurement for AI systems, • Experience supporting multimodal or structured extraction use cases, • Familiarity with authentication and identity integration patterns such as SSO and SAML, • Experience working with Security, data governance, compliance, and procurement partners in enterprise technology delivery, • Familiarity with governance, policy, vendor review, or procurement processes related to enterprise AI tooling, • Experience in nonprofit, public sector, international affairs, or other mission-driven organizations Talent in Action, • Purpose-Driven, • Reliable, • Expertise, • Respectful Collaboration, • Curiosity, • Results-Oriented The salary for this position is determined based on a wide variety of factors, including but not limited to an individual’s professional experience, qualifications, education, and other business needs along with internal equity considerations. Employees are not typically hired at the top of the range for their role, and compensation decisions are based on the aforementioned circumstances. NED also offers a generous benefits package that demonstrates its commitment to employee health and well-being.