Senior Software Engineer ( Java Full-Stack / AI)
Explicitly requires vibe coding skills and use of AI coding assistants like Claude Code, Cursor, and Copilot; focused on building agentic AI and RAG integrations.
About the Role
Senior full-stack engineer role focused on designing and scaling Java-based microservices and REST APIs, owning front-end features, and building agentic AI capabilities that connect large language models to enterprise systems. The position emphasizes hands-on engineering, modern AI tooling (RAG, prompt engineering), and mentorship within agile teams.
Job Description
Role
Senior Software Engineer (Java Full-Stack / AI) responsible for end-to-end ownership of platform components: designing and shipping Java microservices, building secure REST APIs, implementing responsive front-end features, and developing agentic AI capabilities that integrate LLMs with enterprise systems.
Key Responsibilities
- Design, build, and maintain scalable microservices and RESTful APIs
- Implement and own responsive front-end features alongside backend services
- Develop agentic AI features including RAG pipelines and MCP-based integrations to enable secure LLM interactions with internal data and tools
- Apply prompt engineering techniques (few-shot, one-shot, chain-of-thought) in development workflows
- Make pragmatic architecture and design decisions balancing scale, cost, and maintainability
- Write clean, well-tested code and participate actively in code reviews
- Collaborate with product and cross-functional teams to deliver working software
- Help set engineering standards and mentor other developers
Basic Qualifications
- 6+ years of professional software engineering experience (full-stack)
- Strong proficiency in Java and hands-on experience designing and building microservice architectures (Spring Boot or equivalent)
- Experience building clean, secure, maintainable RESTful API endpoints
- Front-end experience with Angular or React
- Experience building RAG (Retrieval-Augmented Generation) applications or pipelines
- Working knowledge of prompt engineering techniques and a solid mental model of LLM behavior
- Comfortable using AI coding assistants (e.g., Claude Code, Cursor, Copilot)
- Strong grasp of relational and/or NoSQL databases and data modeling
- Experience working in Agile teams and delivery processes
Preferred Qualifications
- Python for AI agent logic, MCP server/client development, and custom integrations
- DevOps / cloud experience deploying to production using Docker, Kubernetes, or OpenShift
- Hands-on experience with AWS and CI/CD pipelines
- Familiarity with agent frameworks and orchestration (LangChain, LangGraph, CrewAI, AutoGen, or similar)
- Exposure to LLM SDKs (OpenAI, Anthropic, Google Gemini, Azure OpenAI)
- Experience with vector databases (Pinecone, Weaviate, FAISS, pgvector, ChromaDB)
- Prior experience in a technical lead or mentorship role