CGP / Gemini Enterprise Engineer

This is a fully remote position, open to applicants in United States.

📋 Description

• Design, develop, and implement agentic assistants and GenAI applications on the Gemini Enterprise Agent Platform.

• Establish RAG pipelines and grounding through search and grounding functionalities.

• Integrate the Agent2Agent protocol along with multi-agent orchestration methodologies.

• Assess and choose foundation models based on client requirements, cost considerations, and performance metrics.

• Fine-tune or perform prompt engineering on models to meet accuracy, safety, and compliance standards.

• Oversee model performance and make iterative improvements based on feedback and reviews.

• Create evaluation frameworks and regression test sets to ensure agent accuracy, grounding, and hallucination rates.

• Develop live API and tool-calling integrations with client systems including SIS, ERP, and casework systems.

• Collaborate with Data Engineering and AgentOps on data access, infrastructure, deployment, monitoring, and environment management.

• Keep technical documentation updated regarding solution architecture, model configurations, and integration points.

• Transform one-time client projects into repeatable playbooks and connectors.

• Manage the Forward Deployed Engineer’s delivery backlog, providing estimates, identifying risks, and ensuring timely delivery of solutions.

• Engage in technical discovery sessions to verify feasibility.

• Conduct code and configuration evaluations.

• Act as the quality control gate for release readiness.

• Offer technical insights on scope, risks, and timelines.

⛳️ Requirements

• Practical experience in building and deploying GenAI/agentic AI solutions in production, such as LLM-based assistants, RAG pipelines, or multi-agent orchestration.

• Preferably direct experience with the Gemini Enterprise Agent Platform or Vertex AI; extensive GenAI experience on AWS Bedrock, Azure AI Foundry, OpenAI, or Anthropic APIs is also valuable.

• Knowledge of large language models and skills in prompt engineering, fine-tuning, or grounding techniques.

• Familiarity with the Agent2Agent (A2A) protocol and multi-agent orchestration frameworks.

• Understanding of cloud data, compute, and access-control services that support AI workloads, such as BigQuery/Snowflake, Cloud Run/GKE, and IAM.

• Google Cloud certification is preferred, including Professional Machine Learning Engineer or Professional Cloud Architect.

• Experience in constructing RAG pipelines and integrating LLM-based solutions with enterprise data sources.

• Foundational software engineering skills necessary to create production-quality integrations using Python and/or relevant SDKs.

• Experience in building evaluation frameworks or test suites for LLM/agent outputs and conducting regression tests prior to releases.

• Ability to work from a defined backlog and convert technical requirements into effective solutions.

🏝️ Benefits

• Medical insurance

• Dental insurance

• Vision insurance

• HSA

• FSA

• Generous earned time off

• 401K/student loan repayment

• Life insurance and AD&D insurance

• Employee assistance program

• Employee stock purchase program

• Tuition reimbursement

• Performance-based incentive pay

• Short-term disability

• Long-term disability

• Robust wellness program