What are the responsibilities and job description for the Senior Full Stack AI Engineer position at BrezQ?
Senior Full Stack AI Engineer
Location: Basking Ridge, NJ / Dallas, TX / Tampa, FL (Hybrid/Onsite)
About BrezQ
BrezQ is a technology company specializing in Software Development, Artificial Intelligence, Cloud Engineering, Enterprise Applications, Data Platforms, and Digital Transformation. We build scalable technology solutions that solve complex business problems for enterprise organizations.
Position Overview
We are seeking a Senior Full Stack AI Engineer to design, build, and deploy enterprise-grade AI-powered applications.
This role requires expertise across modern frontend development, backend engineering, cloud-native platforms, API development, and Generative AI technologies.
You will work on building intelligent applications that combine traditional software engineering with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), AI Agents, vector databases, semantic search, and enterprise data integrations.
This is a software engineering role first and an AI role second. Candidates must demonstrate strong engineering fundamentals and production-scale application development experience.
What You Will Build
- AI-powered enterprise web applications.
- Intelligent search and knowledge systems.
- LLM-driven customer and employee experiences.
- AI agents that automate business workflows.
- RAG platforms connected to enterprise knowledge repositories.
- AI-enabled dashboards and decision-support systems.
- Real-time data processing and analytics platforms.
- Enterprise integrations with internal and external systems.
Key Responsibilities
Full Stack Development
- Design and develop scalable web applications.
- Build frontend applications using React and TypeScript.
- Develop backend services and APIs using Java and Spring Boot.
- Design secure and scalable REST APIs.
- Implement authentication, authorization, and access control.
- Optimize application performance and scalability.
AI Engineering
- Integrate Large Language Models into enterprise applications.
- Build Retrieval-Augmented Generation (RAG) solutions.
- Design vector search architectures.
- Develop AI agents and workflow automation systems.
- Implement prompt orchestration and model routing.
- Fine-tune AI application performance and accuracy.
- Design evaluation frameworks for AI outputs.
- Build guardrails, monitoring, and governance controls.
Data Engineering
- Design data ingestion pipelines.
- Build semantic search solutions.
- Integrate structured and unstructured enterprise data.
- Implement vector databases and embedding pipelines.
Cloud & DevOps
- Deploy AI applications in cloud environments.
- Containerize applications using Docker.
- Deploy workloads using Kubernetes.
- Build CI/CD pipelines.
- Implement observability and monitoring.
Required Technical Skills
Frontend
- React
- TypeScript
- JavaScript ES6
- HTML5
- CSS3
- Material UI
- State Management (Redux, Context API)
Backend
- Java 17
- Spring Boot
- Spring Security
- Spring Cloud
- REST APIs
- Microservices Architecture
AI / Generative AI
- OpenAI APIs
- Azure OpenAI
- Anthropic Claude
- Google Gemini
- LangChain
- LangGraph
- LlamaIndex
- Prompt Engineering
- Agent Frameworks
RAG Technologies
- Vector Databases
- Pinecone
- Weaviate
- Chroma
- FAISS
- Semantic Search
- Embeddings
Databases
- PostgreSQL
- MongoDB
- Redis
Cloud
- AWS
- Azure
DevOps
- Docker
- Kubernetes
- GitHub Actions
- Jenkins
Required Experience
- 7 years of software engineering experience.
- 3 years of modern React development.
- 5 years of backend development using Java and Spring Boot.
- 2 years building AI-powered production applications.
- Experience implementing RAG architectures.
- Experience integrating enterprise systems with LLM platforms.
- Experience deploying applications to cloud environments.
- Experience working in Agile product teams.
Preferred Experience
- Telecommunications industry experience.
- Experience building AI copilots.
- Experience with Agentic AI frameworks.
- Experience with Model Context Protocol (MCP).
- Experience with GraphRAG architectures.
- Experience building multi-agent systems.
- Experience with AI governance and security frameworks.