Note: The job is a remote job and is open to candidates in USA. Griting AI is recruiting on behalf of an unnamed enterprise technology client developing an ontology-driven enterprise AI platform. The Senior Full-Stack AI Engineer will build and support customer-facing applications, backend services, and production AI capabilities across the platform.

Responsibilities

• Own customer-facing features end to end, from requirements and technical design through implementation, testing, deployment, and production support
• Build and maintain modern web applications using React, Next.js, and TypeScript
• Develop scalable backend services using Java, Spring Boot, Python, and FastAPI
• Integrate LLMs, AI agents, RAG/GraphRAG, and multi-model orchestration into production applications
• Work with ontology-driven data models, knowledge graphs, and document intelligence capabilities
• Leverage AI-assisted development tools to accelerate implementation while maintaining engineering quality, security, and maintainability
• Build, containerize, and deploy cloud-native services using Docker, Kubernetes, and Helm
• Support production deployments across Google Cloud and Microsoft Azure
• Develop automated tests, troubleshoot complex issues, improve system performance, and maintain service reliability
• Collaborate with cross-functional stakeholders to translate business requirements into reliable software solutions

Skills

• 5–10 years of professional software engineering experience in full-stack or backend-focused development
• Strong proficiency in at least one of TypeScript, Java, or Python, with the ability to work across multiple technology stacks
• Experience developing production web applications using React, Next.js, or similar frameworks
• Experience building backend applications and REST APIs using Spring Boot, FastAPI, or equivalent frameworks
• Solid understanding of relational databases, authentication, authorization, and modern software architecture
• Hands-on experience with Docker, Kubernetes, and a major cloud platform such as GCP or Azure
• Demonstrated ability to use AI coding assistants effectively while independently validating generated code
• Proven experience owning software features from design to production deployment
• Strong foundation in testing, debugging, code reviews, and maintainable software development
• Ability to become productive quickly in unfamiliar, complex codebases
• Experience developing production AI applications involving LLMs, AI agents, RAG, GraphRAG, or multi-model workflows
• Familiarity with OpenAI, Anthropic Claude, Google Vertex AI, Azure OpenAI, or Model Context Protocol (MCP)
• Experience with knowledge graphs, ontology-driven platforms, or document intelligence
• Familiarity with PostgreSQL, Redis, OpenSearch, vector databases, or Apache Kafka
• Experience with event-driven systems, microservices, and workflow orchestration
• Production experience with Java Spring Boot and Python FastAPI
• Familiarity with CI/CD, Helm, GitHub Actions, and observability tools

Benefits

• Full-time US remote role
• Build enterprise-grade AI products that address real-world industrial and engineering challenges
• Work across the full technology stack, including modern frontend applications, distributed backend services, and agentic AI
• Take meaningful ownership of product features and production outcomes
• Apply AI-native engineering practices to accelerate software development
• Contribute to the evolution of an enterprise knowledge and intelligence platform

Company Overview