AI Engineer​/Generative AI Developer San Ramon, CA

Driving innovation in artificial intelligence and generative machine learning systems, Fourways Consulting LLC is actively seeking an accomplished AI Engineer / Generative AI Developer for an exciting onsite engagement in San Ramon, CA. In this vital software engineering and technical leadership role, you will architect, build, and deploy production-grade LLM applications, autonomous agentic workflows, and robust RAG pipelines. Bringing over 8 years of progressive software development experience combined with 2+ years of specialized generative AI expertise, you will empower enterprise clients to scale intelligent automation.

This prestigious career opportunity offers competitive remuneration, high technical visibility, and exceptional professional growth within a premier technology consulting enterprise.

As an AI Engineer / Generative AI Developer supporting Fourways Consulting LLC in San Ramon, CA, you will take full operational, architectural, and tactical ownership of generative AI development, backend integration, and cloud-native model deployment. Your day-to-day responsibilities include designing scalable Python applications, integrating Azure OpenAI models, building multi-agent systems with Auto Gen and CrewAI, and structuring high-performance Retrieval-Augmented Generation (RAG) pipelines using vector databases and Microsoft Graph APIs.

You will collaborate closely with cross-functional software engineering, data science, and product squads in Agile sprint cycles while ensuring uncompromised code quality, security, and CI/CD pipeline automation. Furthermore, you will manage application requirements.

• Architect, design, develop, test, and deploy production-grade generative AI applications and LLM-powered solutions.
• Build and maintain robust backend services, scalable microservices, and secure RESTful APIs utilizing Python.
• Implement multi-agent conversational workflows and orchestration frameworks utilizing Auto Gen, CrewAI, Lang Chain, and Lang Graph.
• Design and optimize high-performance Retrieval-Augmented Generation (RAG) pipelines and vector database integrations.
• Integrate enterprise data services including Microsoft Graph APIs for seamless document retrieval and context enrichment.
• Deploy, scale, and manage AI workloads on Azure OpenAI and cloud-native infrastructure.
• Configure, maintain, and optimize automated CI/CD deployment pipelines and containerized environments.
• Collaborate seamlessly with cross-functional software development, product management, and data science squads.

• Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Software Engineering, or a related technical discipline.
• Minimum of 8+ years of progressive professional software development experience with expert-level proficiency in Python.
• Minimum of 2+ years of dedicated, hands‑on professional expertise in Generative AI, Large Language Models (LLMs), and prompt engineering.
• Strong, demonstrable hands‑on professional experience with Azure OpenAI services and LLM endpoint integration.
• Comprehensive working knowledge and practical proficiency in building agentic AI solutions using Auto Gen, CrewAI, Lang Chain, or Lang Graph.
• Deep practical experience building RAG pipelines, managing vector databases, and optimizing semantic search architectures.
• Solid practical experience integrating Microsoft Graph APIs and configuring automated CI/CD deployment pipelines.
• Mandatory legal work eligibility and physical availability for onsite professional operations (4 days/week) in San Ramon, CA (local or relocation).

• Professional certifications such as Microsoft Certified:
  Azure AI Engineer Associate or…