NorthBay is a global AWS Consulting Partner seeking a high-caliber Senior Generative AI Expert with extensive experience in building Agentic AI applications. The role involves designing and developing AI applications, leading a cross-functional team, and ensuring enterprise-grade security and compliance standards in deployments.
Responsibilities:
- Design and develop Agentic AI applications using LLM frameworks (LangChain, AutoGPT, CrewAI, Semantic Kernel, or similar)
- Architect and implement multi-agent systems for enterprise-grade solutions
- Integrate AI agents with APIs, databases, internal tools, and external SaaS products
- Lead and mentor a cross-functional team across global time zones
- Optimize performance, context retention, tool usage, and cost efficiency
- Build reusable pipelines and modules to support GenAI use cases at scale
- Ensure enterprise-grade security, privacy, and compliance standards in deployments
- Collaborate directly with clients and senior stakeholders
Requirements:
- 5 to 7+ years of software engineering and AI/ML experience
- Experience in autonomous AI agents, tool-using LLMs, LangChain, AutoGPT, or similar frameworks
- Design and develop Agentic AI applications using LLM frameworks (LangChain, AutoGPT, CrewAI, Semantic Kernel, or similar)
- Architect and implement multi-agent systems for enterprise-grade solutions
- Integrate AI agents with APIs, databases, internal tools, and external SaaS products
- Lead and mentor a cross-functional team across global time zones
- Optimize performance, context retention, tool usage, and cost efficiency
- Build reusable pipelines and modules to support GenAI use cases at scale
- Ensure enterprise-grade security, privacy, and compliance standards in deployments
- Collaborate directly with clients and senior stakeholders
- 5 to 8+ years of professional experience in software engineering and AI/ML
- 2+ years of practical experience in LLM-based application development
- Strong track record of delivering Agentic AI systems (not just chatbot interfaces)
- Hands-on experience with LangChain, AutoGPT, CrewAI, ReAct, Semantic Kernel
- Hands-on experience with OpenAI, Claude, Gemini, Mistral, or Llama2
- Hands-on experience with embedding models, vector databases (FAISS, Pinecone, Weaviate, etc.)
- Hands-on experience with prompt engineering, RAG, memory/context management
- Hands-on experience with serverless, Python, Node.js, AWS/GCP/Azure cloud
- Experience leading engineering teams and working with enterprise clients
- Excellent communication, documentation, and stakeholder management skills