Engineer IV, AI & Digital Engineering

X-energy LLC is an AI-first organization focused on accelerating Xe-100 nuclear reactor development through advanced digital engineering and artificial intelligence.

About the role

The AI & Digital Engineering Software Engineer IV contributes to X-energy's Artificial Intelligence (AI) Solutions Tiger Team, designing and building production-ready, AI-native applications, agentic workflows, and platform infrastructure. This role applies modern large language models, agentic AI, and cloud-native engineering practices to transform X-energy's engineering processes from siloed documents into a living, queryable engineering model spanning requirements, design, manufacturing, regulatory, and deployment. Operating with considerable latitude for independent judgment, this engineer directly supports X-energy's mission to set the industry standard for nuclear deployment speed and operational excellence.

Responsibilities

For all tracks:

• Work collaboratively in a tiger-team environment to develop production-ready AI solutions.
• Leverage Claude Code and AI-assisted development tools to accelerate development, prompt iteration, and maintenance tasks.
• Apply knowledge of LLMs and AI systems to support the platform's AI-native architecture.
• Partner with X-energy's systems-engineering, licensing, and quality-assurance organizations to ensure delivered solutions and AI-generated artifacts meet nuclear-engineering and regulatory expectations.
• Document solutions, architecture decisions, and integration patterns; support knowledge transfer to relevant technical teams.
• Implement and maintain development best practices and quality standards.
• Execute core tasks with considerable latitude for independent judgment in a fast-paced, team-oriented environment.
• Perform work in accordance with X-energy quality assurance procedures.
• Maintain professional demeanor and behavior in all forms of communication.
• Perform other duties as assigned by manager.

Specialization Tracks:

Track A — Front-End & Full-Stack

• Design and implement user interfaces using React, TypeScript, Tailwind CSS, and Vite.
• Develop full-stack solutions connecting front-end interfaces to AWS backend services (Lambda, ECS, DynamoDB, and related services).
• Create responsive dashboards and visualization tools for engineering workflows and AI agent interactions.
• Implement real-time communication through WebSockets and REST APIs.
• Support the design of maintainable, scalable front-end solutions for technical and engineering applications.
• Implement secure authentication and authorization systems for enterprise applications.
• Create and maintain CI/CD pipelines for web applications.
• Build proof-of-concept demonstrations to validate solution approaches with stakeholders.
• Conduct user acceptance testing and support feedback loops between users and developers.

Track B — Agentic AI

• Design and implement autonomous agent architectures using AWS Bedrock and related services.
• Develop multi-turn agentic workflows with reasoning, planning, memory management, and tool calling for engineering and business contexts.
• Implement RAG and Graph-RAG systems for enhanced knowledge retrieval, requirements traceability, change-impact analysis, and design reuse.
• Build AI applications for automated requirements extraction, traceability-gap detection, verification-artifact generation, design-review assistance, and cross-discipline consistency checking.
• Develop workflows using LangChain, LangGraph, and AWS Strands, applying safety and alignment controls for regulated engineering.
• Support curation of golden datasets and benchmarks evaluating AI outputs against engineering ground truth.
• Support evaluation and safety pipelines using DeepEval, Ragas, or equivalent self-hostable frameworks within GovCloud boundaries.
• Develop MCP (Model Context Protocol) tools exposing engineering systems and reasoning capabilities to the platform and external AI clients.
• Research and support implementation of emerging techniques in autonomous agent development.

Track C — Data & Systems Integration

• Support the design and build of the AWS-native data lakehouse / Common Data Environment using S3, Apache Iceberg, AWS Glue Data Catalog, Lake Formation, and Athena.
• Contribute to the canonical engineering data model spanning Xe-100 requirements, bill-of-materials (BOM), configuration items, test and simulation results, quality records, and digital-thread artifacts.
• Support schema governance, data contracts, schema registry, versioning, backward-compatibility rules, and deprecation workflows.
• Implement a tiered data-classification model enforced at the data layer via Lake Formation tag-based access control and row/column-level security.
• Implement data lineage and provenance tracking supporting NQA-1 audit and 10 CFR 50 Appendix B traceability.
• Build Change Data Capture (CDC) and event-driven pipelines synchronizing authoritative systems into the lakehouse.
• Support integrations between customer, partner, and supplier engineering systems (Siemens Teamcenter, PTC Windchill, Dassault 3DEXPERIENCE, Aras Innovator, Siemens Polarion, IBM DOORS/DOORS Next, Jama Connect, Oracle Primavera P6, Procore, SAP ERP, Box) and X-energy's platform.
• Parse, normalize, and map specialized engineering data formats including STEP, JT, IFC, ReqIF, SysML v2 XMI, QIF, DWG/RVT, and proprietary PLM exports.
• Support identity federation design for external partners and enforce export control and data residency at the integration boundary.
• Support definition of API contracts and versioning strategies; monitor and troubleshoot cross-organizational data flows.
• Support data-quality standards, validation pipelines, and metric dashboards feeding AI agent eval harnesses and NRC submission workflows.

Track D — Platform Infrastructure & DevOps

• Design, build, and maintain containerized applications using Docker, including image building, testing, versioning, and optimization.
• Develop and maintain GitLab CI/CD pipelines, including runner configuration, pipeline optimization, and automated testing workflows.
• Support the architecture of AWS infrastructure using Terraform, including ECS, ECR, VPC, EC2, ALB/NLB, and other cloud services.
• Administer and optimize AWS data services including DocumentDB, OpenSearch, Redis, Aurora Postgres, DynamoDB, and S3.
• Implement and maintain monitoring, alerting, and observability solutions using Datadog and CloudWatch.
• Support security and compliance requirements, including ACM certificate management and security best practices.
• Contribute to release engineering efforts, including versioning strategies, deployment automation, and rollback procedures.
• Create testing frameworks for validating system behavior in serverless environments.
• Implement versioning and governance for code and dependencies.
• Collaborate with development teams to optimize application performance and troubleshoot production issues.
• Participate in on-call rotation to support system reliability and incident response.

Product-management and technical-leadership activities are woven across all tracks. Depending on scope, an engineer may:

• Contribute to technical specifications and roadmaps aligned with engineering needs.
• Serve as a technical point of contact between the development team and internal customers.
• Help track product metrics and success criteria.
• Support evaluation and selection of appropriate AWS services.
• Produce system architecture diagrams and API documentation.
• Participate in technical reviews and code walkthroughs.
• Develop technical prototypes and proof-of-concepts.

Requirements

Minimum Qualifications Required of all applicants:

• Bachelor's degree in Computer Science, Artificial Intelligence, Systems Engineering, Engineering, or a related field from an accredited university or college.
• Typically, ten years of relevant software engineering experience, including experience in one or more of the specialization tracks described above.
• Experience with Git, GitLab, CI/CD, and modern development workflows.
• Proficiency with Jira, Confluence, and AI-enhanced development environments (Claude Code or similar AI-assisted development tools).
• Experience working in collaborative, fast-paced development teams.
• Strong written and verbal communication skills, including the ability to explain complex technical concepts to both technical and non-technical audiences.
• Ability to work a hybrid schedule in the Rockville, MD office Tuesday, Wednesday, and Thursday.

Additional qualifications by track (meet the requirements of at least one track):

Track A — Front-End & Full-Stack

• Working knowledge of React, TypeScript, and modern JavaScript development; experience with Vite, Bun, and Tailwind CSS.
• Proficiency implementing WebSockets and REST APIs.
• Background developing user interfaces for technical or engineering applications.
• Experience with AWS services for web-application deployment.

Track B — Agentic AI

• Working knowledge of modern large language models, agentic architectures, and multi-turn agent workflows.
• Hands-on experience with at least one of AWS Bedrock, AWS Strands, LangChain, LangGraph, or LlamaIndex.
• Working knowledge of RAG and Graph-RAG, including vector search, hybrid retrieval, re-ranking, and chunking.
• Proficiency in TypeScript and Python; familiarity with Node.js/Express and a Python web framework (FastAPI or similar).
• Familiarity with AI evaluation methodology and exposure to eval pipelines using DeepEval, Ragas, Arize Phoenix, or equivalent.
• Working understanding of AWS AI services, particularly AWS Bedrock.

Track C — Data & Systems Integration

No additional track-specific qualifications listed beyond general requirements.

Track D — Platform Infrastructure & DevOps

No additional track-specific qualifications listed beyond general requirements.

Schedule

Hybrid schedule requiring in-office presence in Rockville, MD on Tuesday, Wednesday, and Thursday.