Gen AI Architect

Location: Bridgewater, NJ Persistent Office Full-time only Experience: 12 to 15 Years We are seeking a highly experienced Agentic AI / Generative AI Architect with 15+ years of software and solution architecture experience, combined with handson expertise in Data Science, Machine Learning, and modern agent-based AI systems. This role requires deep technical leadership in designing, implementing, and governing advanced multi-agent AI ecosystems, RAG pipelines, cloud-native AI platforms, and GenAI engineering practices. The ideal candidate will drive endtoend solution architecture for enterprise-grade AI applications while ensuring scalability, robustness, security, and operational excellence. What You'll Do Design & Implement Agentic AI Systems Architect and build multi-agent, goal-driven, autonomous AI systems using frameworks such as: AutoGen LangGraph CrewAI Create intelligent agent ecosystems supporting orchestration, reasoning, and collaborative task execution. Prompt Engineering & LLM Expertise Apply advanced prompt engineering techniques including: Few-shot prompting Chain-of-thought reasoning Prompt templates Optimize prompt flows for deterministic, scalable LLM-driven systems Cloud-Native AI Architecture Design and deploy AI/LLM systems on cloud platforms such as AWS Bedrock, Azure OpenAI, Google Vertex AI, etc. Ensure solutions meet enterprise NFRs including performance, security, cost-optimization, and availability. RAG Pipelines, Vector Databases & MCP Architect and deploy RAG pipelines using vector databases such as: Pinecone Weaviate ChromaDB FAISS Implement MCP Servers and Agent-to-Agent (A2A) communication frameworks. LMOPs / GenAIOPs Implement end-to-end operational pipelines for GenAI applications including: Continuous integration & deployment Model monitoring & drift detection Logging, observability, and troubleshooting mechanisms Establish governance models, reusable patterns, and GenAI best practices. Application & Microservices Architecture Design microservices-based systems using Spring Boot, REST APIs, and secure API design patterns. Implement API security, versioning, and distributed system governance. Architect cloud-native applications using AWS/Azure/Google Cloud Platform, Spring Cloud, PCF, or equivalent. Collaboration & Leadership Work closely with Data Scientists, Product Owners, Business SMEs, and Engineering teams. Lead end-to-end solution architecture for enterprise AI initiatives. Conduct technical presentations, architectural reviews, and stakeholder communication. Expertise You'll Bring 5+ years in software/solution architecture. Proven experience as a Data Scientist or ML Engineer with exposure to agentic AI systems. Experience designing multi-agent systems using AutoGen, LangGraph, CrewAI, etc. Strong understanding of cloud AI platforms (Bedrock, Azure OpenAI, Vertex AI). Hands-on experience with AI Code Assist tools such as: GitHub Copilot Windsurf Cursor AWS Q Expertise in Vector Databases, RAG pipelines, MCP, and multi-agent communication. Strong proficiency in Python (preferred), and optionally Java/Node.js. Experience with microservices, Spring Boot, REST APIs, API security, and versioning. Proficiency in Docker, Kubernetes, CI/CD pipelines. Strong grasp of design patterns and architecture principles. Deep understanding of cloud-native design and distributed systems. Experience designing AI systems that meet NFRs: scalability, security, performance, maintainability. Exceptional communication and presentation skills. Ability to articulate complex AI concepts to technical and non-technical audiences. Strong leadership, problem-solving mindset, and strategic thinking abilities. Ability to collaborate with cross-functional teams to translate business needs into AI-powered solutions. Show more Show less