Senior Technical Solutions Consultant, Agent Assist, Applied AI

Minimum qualifications:

• Bachelor's degree in Science, Technology, Engineering, Mathematics, or equivalent practical experience.
  
• 6 years of experience in solution engineering.
• 3 years of experience in stakeholder management, professional services, or technical consulting.
• 3 years of experience writing code in one or more programming languages (e.g., Python, Java).
• Experience with LLMs, prompt engineering, and conversational AI frameworks (e.g., Vertex AI Agent Space, CX Insights).

Preferred qualifications:

• Experience leading multi-disciplinary technical teams and managing high-stakes projects with CXO-level visibility.
• Experience implementing advanced security protocols, including Cloud DLP for PII redaction and responsible AI filtering at scale.
  
• Experience creating reusable technical assets that have been adopted across an organization.
• Proven ability to design and deploy "Agent OS" architectures that unify LLMs with complex legacy enterprise software stacks.
• Ability to translate highly technical AI concepts into strategic business value for non-technical executive stakeholders.
• Expertise with the broader GenAI ecosystem, including LangChain, Vector Search, and enterprise telephony/contact center integrations (e.g., Genesys, NICE, Five9).

About the job:

The Cloud Applied AI (AAI) powers business growth with Gemini Enterprise. Our portfolio includes Gemini Enterprise for customer experience, along with other vertical and domain packaged solutions. We enable high adoption and speed to value by building solutions that are quickly deployed, delivering new 0-to-1 capabilities with startup agility. Team members operate at the forefront of AI, collaborating directly with model builders with unprecedented speed. Join us to work on cutting-edge projects and shape the future of AI in a fast-paced, collaborative, and impactful environment.

Responsibilities:

• Lead global technical engagements, designing core agent architectures—including reasoning, toolsets, and guardrails—for production-ready enterprise deployments.
• Optimize complex RAG pipelines and prompt chains while integrating non-deterministic LLM outputs with deterministic systems like Salesforce and SAP.
• Oversee enterprise-grade evaluation pipelines using "gold datasets" and LLM-as-a-judge methodologies to ensure high accuracy and brand safety.
• Act as a critical feedback loop for Google Cloud Product and Engineering teams, shaping the AI portfolio through field intelligence.
• Design scalable data ingestion pipelines and author global architectural patterns while providing technical mentorship and code reviews.