GCP / Gemini Enterprise Engineer

Nelnet is a diversified and innovative company committed to enriching lives through the power of service as a student loan servicer, professional services company, consumer loan originator and servicer, payments processor, renewable energy solutions, and K-12 and higher education expert. For over 40 years, Nelnet has been serving its customers, associates, and communities.

The perks of working at Nelnet go beyond our benefits package. When you join the Nelnet team, you're part of a community invested in the success of each individual. That support comes through in our work, as we are united by our mission of creating opportunities for people where they live, learn, and work.

This role owns the technical build and deployment of Nelnet’s GenAI solutions on Google Cloud, specifically the Gemini Enterprise Agent Platform — Google’s 2026 evolution of Vertex AI, unifying model selection, agent building, and orchestration with what were formerly separate Vertex AI and Agentspace products. The GCP / Gemini Enterprise Engineer translates the Forward Deployed Engineer’s scoped delivery backlog into working agentic solutions, model integrations, and data connections that meet client requirements and Nelnet’s engineering standards.
Operating as the core build engineer within Nelnet’s GenAI delivery team, this role is responsible for the technical implementation of agentic assistants, retrieval-augmented generation (RAG) pipelines, and model integrations for higher education and SLED clients, in close collaboration with the Data Engineer on data readiness and the AgentOps Engineer on infrastructure and deployment. The Forward Deployed Engineer and Engagement Manager own client scoping and relationship management; this role owns solution build quality, technical architecture, and delivery execution.
Comepnsation range for this role: $130,000-$150,000 based on experience

Key Responsibilities:

Agentic Solution Development

• Design, build, and deploy agentic assistants and GenAI applications on the Gemini Enterprise Agent Platform (Agent Builder, Workspace Studio, Model Garden), translating backlog items from the Forward Deployed Engineer into working solutions.

• Implement retrieval-augmented generation (RAG) pipelines and grounding using the platform’s search and grounding capabilities.

• Integrate Agent2Agent (A2A) protocol and multi-agent orchestration patterns where engagements require them.

Model Selection & Tuning

• Evaluate and select appropriate foundation models from Model Garden (including Gemini and third-party models) based on client use case, cost, and performance requirements.

• Fine-tune or prompt-engineer models to meet accuracy, safety, and compliance requirements specific to higher education and SLED data.

• Monitor model performance and iterate based on client feedback and delivery retrospectives.

• Build and maintain evaluation harnesses and regression test sets to validate agent accuracy, grounding, and hallucination rates prior to release, with added rigor for student-facing and FERPA-sensitive use cases.

Platform & Integration Engineering

• Build live API and tool-calling integrations so agentic solutions can take real-time actions in client systems (SIS, ERP, casework systems) — distinct from the batch data pipelines the Data Engineer builds for analytics and RAG ingestion; partner with the Data Engineer on shared data access patterns and the AgentOps Engineer on infrastructure.

• Maintain technical documentation of solution architecture, model configurations, and integration points for internal reuse.

• Build solutions for reuse across engagements, converting one-off client work into repeatable playbooks and connectors.

Delivery Execution & Quality

• Execute against the delivery backlog owned by the Forward Deployed Engineer, providing technical estimates, flagging build risks, and delivering working solutions on schedule.

• Participate in technical discovery sessions with the Forward Deployed Engineer to validate feasibility before commitments are made to clients.

• Conduct code and configuration reviews to maintain quality and security standards across the practice.

• Serve as the quality gate in release readiness, confirming evaluation and regression test results before a build moves to production, alongside the AgentOps Engineer’s operational readiness sign-off.

Cross-Functional Collaboration

• Partner with the Data Engineer to ensure data pipelines and classification support agentic solution requirements.

• Partner with the AgentOps Engineer on deployment, monitoring, and environment management.

• Provide technical input to the Forward Deployed Engineer and Engagement Manager on scope, risk, and timeline.

Required Skills and Experience:

• Hands-on experience building and deploying GenAI/agentic AI solutions (e.g., LLM-based assistants, RAG pipelines, multi-agent orchestration) in production — required. Direct experience with the Gemini Enterprise Agent Platform (Agent Builder, Model Garden, Workspace Studio) or its predecessor Vertex AI strongly preferred; candidates with deep GenAI experience on other platforms (e.g., AWS Bedrock, Azure AI Foundry, OpenAI/Anthropic APIs) who can ramp quickly on Google's stack will be considered.

• Experience with large language models and prompt engineering, fine-tuning, or grounding techniques; direct experience with Gemini models (Gemini API / Gemini Enterprise) preferred.

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

• Working knowledge of cloud data, compute, and access-control services supporting AI workloads (e.g., BigQuery/Snowflake, Cloud Run/GKE or equivalent container platforms, IAM) sufficient to ramp quickly on Google Cloud's specific implementations.

• Google Cloud certification preferred (Professional Machine Learning Engineer or Professional Cloud Architect), demonstrating hands-on technical fluency; foundational/business-oriented certifications (e.g., Generative AI Leader) do not satisfy this preference.

• Experience building retrieval-augmented generation (RAG) pipelines and integrating LLM-based solutions with enterprise data sources.

• Software engineering fundamentals sufficient to build production-quality, maintainable integrations (Python and/or relevant SDKs).

• Experience building evaluation harnesses or test suites for LLM/agent outputs (accuracy, groundedness, hallucination rate) and running regression tests before releases.

• Ability to work from a scoped backlog and translate technical requirements from the Forward Deployed Engineer into working solutions.

Desired Competencies:

• Demonstrates strong technical judgment in selecting the right model, architecture, and approach for a given client constraint.

• Builds for reuse, translating one-off client work into repeatable technical assets.

• Communicates technical trade-offs clearly to the Forward Deployed Engineer and Engagement Manager.

• Adapts quickly to platform and product changes given the pace of change in Google’s AI product stack.

• Takes ownership of solution quality from build through deployment.

• Collaborates effectively with Data Engineering and AgentOps counterparts.

• Maintains composure and problem-solving focus when technical blockers threaten delivery timelines.

• Seeks continuous learning given the fast-evolving nature of the Google Cloud AI and agent platform.

Our benefits package includes medical, dental, vision, HSA and FSA, generous earned time off, 401K/student loan repayment, life insurance & AD&D insurance, employee assistance program, employee stock purchase program, tuition reimbursement, performance-based incentive pay, short- and long-term disability, and a robust wellness program. Click here to learn more about our benefits: Benefits & Perks - Nelnet Inc.

Nelnet is committed to providing a welcoming and respectful workplace where all associates have the opportunity to succeed. As an Equal Opportunity Employer, we ensure that all qualified applicants are considered for employment. Employment decisions are made without regard to race, color, religion/creed, national origin, gender, sex, marital status, age, disability, use of a guide dog or service animal, sexual orientation, military/veteran status, or any other status protected by federal, state, or local law. We value the unique contributions of every team member and believe that a positive work environment benefits everyone.  

Qualified individuals with disabilities who require reasonable accommodations in order to apply or compete for positions at Nelnet may request such accommodations by contacting Talent Acquisition at 402-486-5725 or [email protected].

Nelnet is a Drug Free and Tobacco Free Workplace.

Use of Artificial Intelligence in Hiring

We may use automated or artificial intelligence enabled tools to assist with the initial review of applications, such as identifying relevant skills or experience. These tools are used to support human review and do not make hiring decisions. A recruiter reviews applications and determines which candidates move forward in the hiring process. For more information, see our Privacy Policy and Pre-Use Notice: Automated Tools in Hiring