Gen AI Architect

• Design, architect, and implement scalable enterprise Generative AI solutions.
• Build and deploy production-grade Gen AI applications using modern LLM frameworks and cloud technologies.
• Develop and showcase innovative Gen AI Proofs of Concept (POCs) that address business challenges.
• Design and implement Agentic AI systems, including autonomous workflows, planning, reasoning, memory, and tool orchestration.
• Develop robust Python-based AI applications and services with production-quality code.
• Design and implement Retrieval-Augmented Generation (RAG) architectures using vector databases and enterprise data sources.
• Collaborate with business stakeholders, product teams, and engineering teams to translate requirements into AI solutions.
• Evaluate foundation models and recommend the appropriate architecture based on use cases.
• Optimize AI solutions for scalability, security, latency, and cost.
• Mentor engineering teams on Gen AI best practices, architecture patterns, and implementation strategies.

Required Technical Skills

• Python
• Large Language Models (OpenAI, Anthropic, Llama, Gemini, etc.)
• LangChain, LangGraph, LlamaIndex, or similar orchestration frameworks
• Agentic AI frameworks and autonomous AI systems
• Retrieval-Augmented Generation (RAG)
• Vector databases (Pinecone, Weaviate, Chroma, Milvus, FAISS, etc.)
• Prompt Engineering
• AI orchestration and workflow automation
• REST APIs and microservices
• Git, CI/CD, Docker, Kubernetes
• Cloud platforms (AWS, Azure, or Google Cloud)

• Hands-on Gen AI Architect, hybrid work 3-4 days in Raritan, NJ.
• Must have implemented Gen AI solutions in production, not just POCs.