Role Overview
Design, build, and deploy AI-enabled, cloud-native full-stack applications using Java, Python, React, and AWS. Integrate Generative AI and LLM capabilities (RAG, vector retrieval, prompt engineering, agents) into enterprise applications. Own components end-to-end, collaborate across frontend, backend, AI, cloud, and data layers, and communicate technical decisions to stakeholders.
Responsibilities
- Develop backend services and APIs with Java/Spring Boot and/or Python, integrating enterprise systems and AI services.
- Build responsive UIs with React and TypeScript/JavaScript, integrating with secure backend APIs and AI-powered services.
- Apply AI-assisted engineering techniques to accelerate coding, testing, documentation, and code review.
- Design and deploy solutions on AWS using cloud-native compute, integration, data, and AI services.
- Build secure, scalable API-led, microservices, and event-driven architectures.
- Implement automated unit, integration, API, and UI testing with AI behavior evaluation.
- Apply DevSecOps, CI/CD, Infrastructure as Code, and containerization for repeatable pipelines.
- Embed security, responsible AI, privacy, reliability, observability, and governance from design to production.
Requirements
- Strong proficiency in Java and/or Python for backend development.
- Expertise in React and TypeScript/JavaScript for frontend development.
- Hands-on experience with AWS cloud services and cloud-native architectures.
- Practical knowledge of Generative AI, LLMs, RAG, vector databases, prompt engineering, and agent orchestration.
- Experience with Spring Boot, microservices, event-driven systems, CI/CD, IaC, and containerization (Docker/Kubernetes).
- Ability to own workstreams end-to-end and communicate clearly with technical and business stakeholders.