AI Software Engineer

Kforce has a client in Hopkins, MN that is seeking an AI Software Engineer (Python/Java-Spring Boot/React/GenAI/Full-Stack). Summary We are seeking a full-stack engineer skilled in Python and Java (Spring Boot), experienced with modern backend frameworks and React-based frontend development, and capable of delivering production-grade GenAI solutions (LLMs, RAG, Agents, MCP, guardrails). The candidate should be able to design, build, and operate scalable services and applications using modern AI patterns with strong software craftsmanship. Responsibilities:

• Build backend services in Python (Flask, FastAPI, Django) and Java (Spring Boot); Design clean APIs, integrations, and background jobs
• Develop user interfaces using React (preferred); Collaborate on UX, component libraries, accessibility, and performance
• Own quality with PyTest/JUnit, integration and contract testing; enable CI/CD automation
• Deliver GenAI capabilities: prompt design, RAG pipelines, agent orchestration, and workflow automation
• Productionize AI with guardrails for safety, compliance, observability, and fallback strategies; Measure latency, cost, and accuracy
• Work across data layers: vector stores, relational DBs, caching, and secure connectors; Ensure data privacy and governance
• Collaborate across product, design, and platform teams; review code, architect solutions, document decisions, and mentor peers
• BS/MS in Computer Science or equivalent experience
• 8+ years of experience leading architecture, cross-team design, and AI governance

• Strong in Python and Java (Spring Boot) - APIs, microservices, async processing, and performance optimization
• Frameworks: Flask, FastAPI, Django, Spring Boot (REST, security, data, microservices)
• API design (REST/JSON), OpenAPI, OAuth/OIDC, JWT, RBAC

• React (preferred) or Angular: component design, state management, routing, testing (Jest, Playwright)
• Build tooling: Vite/Webpack, npm/yarn

• LLM fundamentals, embeddings, prompt design, tool/function calling
• RAG architectures and evaluation approaches
• Agents: orchestration, memory, multi-agent patterns
• MCP, guardrails, and secure AI patterns
• Frameworks: LangChain/LangGraph, CrewAI (plus Haystack/LlamaIndex familiarity)

• Vector DBs, PostgreSQL/MySQL, Redis
• Cloud & DevOps: Docker, Kubernetes, CI/CD, observability
• Messaging/streaming: Kafka/MQ; batch vs. real-time processing
• Cloud & DevOps: Azure (preferred) and Azure AI services, Docker, Kubernetes
• Hands-on with AKS, EKS deployments, Helm charts, and CI/CD pipelines (Azure DevOps, GitHub Actions, Jenkins)

• Experience delivering production-grade GenAI applications with measurable outcomes
• Integration with LLM providers (OpenAI, Anthropic, local models)
• AI observability, evaluation frameworks, and guardrail telemetry
• Financial services/regulated environment experience