Job Title: Sr. Java Backend AI platform Developer (Agentic AI/LLM)
Location: Irving, TX (Hybrid)
Duration: 12+ Months
About the Role:
We are seeking a Senior Software Engineer to lead backend development for our cutting-edge, multi-tenant Enterprise AI Assistant Platform. In this role, you will design and scale robust microservices that power multi-LLM routing, real-time streaming, and cross-device synchronization. You will work at the intersection of reactive programming, strict multi-tenant database architecture, and advanced AI tool integrations to deliver a secure, highly responsive chat experience at an enterprise scale.
Key Responsibilities:
Reactive & Real-Time Systems: Develop non-blocking, real-time AI chat capabilities using Spring WebFlux, R2DBC, and Server-Sent Events (SSE) to stream AI responses without exhausting server threads.
Multi-Tenant Architecture: Architect dynamic database routing and automated schema migrations across distinct, dynamically provisioned PostgreSQL tenant databases using Flyway to ensure ironclad data isolation.
AI & LLM Integration (Adapter Pattern): Build provider-agnostic adapter interfaces to seamlessly route requests across multiple LLM providers (e.g., Azure OpenAI, standard OpenAI, LiteLLM) to prevent vendor lock-in.
Platform Engineering: Design and implement highly scalable backend microservices using Java 17 (or Kotlin) and Spring Boot 3.x.
Extensibility & Tooling: Implement Model Context Protocol (MCP) servers and tools, alongside Retrieval-Augmented Generation (RAG) and Vector Store capabilities (AWS S3), to extend the AI's reasoning and secure access to company data.
Security & Identity: Secure APIs and SDKs implementing robust authentication flows, including JWT Bearer Tokens, HMAC request signing, and Role-Based Access Control (RBAC).
Multi-Tenant Architecture: Architect dynamic database routing and automated schema migrations across distinct, dynamically provisioned PostgreSQL tenant databases using Flyway to ensure ironclad data isolation.
AI & LLM Integration (Adapter Pattern): Build provider-agnostic adapter interfaces to seamlessly route requests across multiple LLM providers (e.g., Azure OpenAI, standard OpenAI, LiteLLM) to prevent vendor lock-in.
Platform Engineering: Design and implement highly scalable backend microservices using Java 17 (or Kotlin) and Spring Boot 3.x.
Extensibility & Tooling: Implement Model Context Protocol (MCP) servers and tools, alongside Retrieval-Augmented Generation (RAG) and Vector Store capabilities (AWS S3), to extend the AI's reasoning and secure access to company data.
Security & Identity: Secure APIs and SDKs implementing robust authentication flows, including JWT Bearer Tokens, HMAC request signing, and Role-Based Access Control (RBAC).
Required Qualifications:
Extensive experience building enterprise applications with Java 17 and/or Kotlin.
Crucial: Deep expertise in reactive programming using Spring WebFlux and Project Reactor (Mono/Flux).
Crucial: Experience with reactive database drivers, specifically R2DBC, rather than traditional blocking JDBC/JPA.
Proven track record of designing secure, multi-tenant backend architectures with tenant-level database isolation and dynamic routing.
Experience configuring and deploying cloud services, specifically AWS S3 (pre-signed URLs) and AWS Secrets Manager.
Crucial: Deep expertise in reactive programming using Spring WebFlux and Project Reactor (Mono/Flux).
Crucial: Experience with reactive database drivers, specifically R2DBC, rather than traditional blocking JDBC/JPA.
Proven track record of designing secure, multi-tenant backend architectures with tenant-level database isolation and dynamic routing.
Experience configuring and deploying cloud services, specifically AWS S3 (pre-signed URLs) and AWS Secrets Manager.
Preferred Qualifications:
Experience integrating generative AI models and external tooling frameworks (e.g., Spring AI, MCP, LangChain).
Familiarity with modern observability tools (Prometheus, Micrometer, Spring Actuator).
Experience integrating generative AI models and external tooling frameworks (e.g., Spring AI, MCP, LangChain).
Familiarity with modern observability tools (Prometheus, Micrometer, Spring Actuator).