AI Engineer

An on-site AI Engineer role based in New Jersey, focused on designing, developing, and deploying AI-powered applications and agentic workflows in production using LLMs, Retrieval-Augmented Generation, and prompt engineering. Collaboration spans AI architecture, development (Java and frontend), and QA (Playwright) to deliver enterprise-grade AI solutions.

• Design, develop, and deploy AI powered applications leveraging contemporary LLM technologies.
• Create and implement agentic workflows using AI agents, orchestration frameworks, and automation platforms.
• Build Retrieval-Augmented Generation pipelines employing vector databases and enterprise knowledge sources.
• Conduct prompt engineering, optimization, and model evaluation to improve AI accuracy and reliability.
• Fine-tune foundation models when needed to satisfy business requirements.
• Integrate AI capabilities into existing enterprise applications and platforms.
• Monitor, optimize, and sustain AI systems in production environments.
• Develop backend services and RESTful APIs using Java frameworks.
• Create responsive, scalable frontend applications to deliver AI driven user experiences.
• Collaborate with architects, product owners, and business stakeholders to translate requirements into technical solutions.
• Implement integrations with internal and external systems via APIs and microservices.
• Develop automated testing strategies for AI-enabled applications.
• Design and execute UI and API automation using Playwright.
• Validate AI outputs through functional, regression, and performance testing.
• Establish testing frameworks and quality gates for AI solutions deployed in production.
• Ensure security, performance, and reliability standards are met.
• Work closely with AI Architects, Data Scientists, Product Teams, and Business SMEs.
• Stay current with emerging AI technologies, frameworks, and industry best practices.
• Contribute to AI governance, responsible AI practices, and solution documentation.

• Prompt engineering proficiency.
• Experience with Large Language Models including OpenAI, Azure OpenAI, Anthropic, Gemini, and others.
• Proficiency with agentic AI frameworks.
• Expertise in Retrieval-Augmented Generation (RAG).
• Knowledge of vector databases.
• Experience with model evaluation and optimization.
• Understanding of fine-tuning concepts.
• AI application development experience.
• Experience with AI orchestration frameworks such as Lang Chain, Lang Graph, Semantic Kernel, CrewAI, Auto Gen, etc.
• Java 8, 11, or 17+ development experience.
• Spring Boot expertise.
• REST APIs and microservices architecture experience.
• API integration skills.
• Frontend experience with React.js, Angular, or other modern JavaScript frameworks.
• HTML5, CSS3, JavaScript, and Type Script proficiency.
• Playwright automation experience.
• API testing experience.
• Test automation framework design experience.
• Functional regression testing experience.
• CI/CD testing practices knowledge.
• Experience with Azure, AWS, or GCP clouds.
• Docker and Kubernetes experience.
• CI/CD pipelines experience.
• Git, Git Hub, and Azure Dev Ops familiarity.

• Core programming and backend:
  Java (8/11/17+), Spring Boot, REST APIs, microservices
• Frontend stack:
  React.js, Angular, modern JavaScript frameworks, HTML5, CSS3, JavaScript, Type Script
• AI and ML tooling:
  OpenAI family, Azure OpenAI, Anthropic, Gemini;
  Lang Chain, Lang Graph, Semantic Kernel, CrewAI, Auto Gen;
  Retrieval-Augmented Generation; vector databases
• Cloud and containers:
  Azure, AWS, GCP, Docker, Kubernetes
• Version control and Dev Ops:
  Git, Git Hub, Azure Dev Ops
• Testing and automation:
  Playwright automation, API testing, test automation frameworks, functional regression testing, CI/CD testing practices