Senior Deployed AI Engineer (Gemini) (PCS920)

Overseas; Comisión de Fomento de Perú; Hybrid; ARS 172,948,000 - 311,307,000; Full time

Benefits offered by this job

USD compensation

Bi-monthly pay

Paid time off

Holidays observed

Job summary

Overseas is seeking a Senior Deployed AI Engineer (Gemini) to design, build, and deliver full-stack AI products for enterprise clients. You will own frontend, backend, data pipelines, deployment, and evaluation, collaborating with international teams to translate new Google AI capabilities into client value.

You will work with Gemini models, Vertex AI, ADK, and agent frameworks, ensuring production-quality pipelines, governance, and tooling.

Qualifications

• 3–5 years of software or data engineering with extensive hands-on AI tools and recent LLM development.
• Strong hands-on with Google AI stack: Gemini, Vertex AI, Gemini Enterprise or ADK; production deployments.

Responsibilities

• Develop user-facing interfaces in TypeScript and React and backend services in Python/Node.
• Build retrieval-augmented generation pipelines with embeddings and vector search.
• Design and deploy Gemini Enterprise components, incl. Agent Designer and Inbox.
• Connect Gemini Enterprise to client landscapes with proper permissions and governance.
• Write evaluation suites and tests; monitor cost, latency, and quality in production.
• Deploy on cloud infra (GCP/AWS/Azure) and maintain data pipelines feeding AI systems.

Skills

English proficiency

Client communication

Mentoring

Problem solving

Education

Bachelor's or Master's in CS/Engineering

Tools

Python

TypeScript/JavaScript

React

Vertex AI

Gemini Enterprise

Google ADK

LangChain/LangGraph

Claude Code/Cursor

BigQuery

GCP/AWS/Azure

Job description

Senior Deployed AI Engineer (Gemini)

Peru, Argentina, Brazil

Remote

About Our Client

Our client is a global data and AI consulting firm serving enterprise clients across multiple industries, including FMCG, financial services, healthcare, manufacturing, and the public sector, with a team of data and AI experts spread across 20+ countries.

About the Role

We're looking for a Senior Deployed AI Engineer specialized in Gemini Enterprise and the Google AI stack to design, build, and deliver full-stack AI products for enterprise clients. You'll work embedded with clients, take AI features from idea to production, and serve as the team's reference for Google's enterprise AI platform.

You'll own your components end to end: the front end, the service behind it, the data and retrieval pipelines feeding it, the deployment, and the evaluations proving it works. Beyond Google platform depth, you'll be expected to deliver confidently across the full stack, including full-stack development, data engineering, cloud infrastructure, and client communication.

Responsibilities

• Develop user-facing interfaces in TypeScript and React, along with the backend services and APIs behind them in Python or Node
• Implement agentic behavior including orchestration, tool and function calling, memory, and guardrails
• Build retrieval-augmented generation pipelines covering ingestion, chunking, embeddings, and vector and hybrid search
• Design and build agents with Gemini models, Vertex AI, the Agent Development Kit, and Agent Engine
• Implement and configure Gemini Enterprise for clients, including Agent Designer, the Inbox for managing long-running agents, and agent sandboxes
• Connect Gemini Enterprise to client application landscapes through first-party and partner connectors with proper permissions, governance, and auditability
• Build grounded, retrieval-backed applications with Vertex AI Search, RAG Engine, grounding with Google Search, and BigQuery as the data backbone
• Implement agent interoperability through the A2A protocol and MCP, and track Google's releases closely to translate new capabilities into client value
• Write evaluation suites and regression tests for LLM-powered features, monitoring cost, latency, and quality in production
• Deploy on cloud infrastructure across GCP, Azure, or AWS, and build and maintain the data pipelines feeding AI systems
• Use agentic coding tools such as Claude Code, Gemini CLI, Codex, or Cursor daily with good judgment about verification and review
• Communicate progress, trade-offs, and blockers clearly to clients and project leads, and support pre-sales when needed
• Mentor junior engineers and contribute to internal accelerators, reusable components, and engineering standards

What We're Looking For

• 3 to 5 years of software or data engineering experience, with extensive hands-on use of AI tools and LLM-based development over the past year
• Strong hands-on experience with the Google AI stack, including Gemini models, Vertex AI, and ideally Gemini Enterprise or ADK, with at least one solution taken to production on GCP
• Strong programming skills in Python and TypeScript or JavaScript, with experience building and consuming APIs
• Experience with front-end development in React or similar frameworks, and at least one backend framework
• Hands-on experience with RAG, embeddings, and vector search, and with at least one agentic framework such as Google ADK, LangGraph, or LangChain
• Strong working experience with GCP; Azure or AWS is a plus
• Fluency with agentic coding tools such as Claude Code, Gemini CLI, Codex, or Cursor, and experience building and maintaining data pipelines
• Professional English proficiency at C1 or C2 level minimum, as you'll work daily with international clients and colleagues
• Bachelor's or Master's degree in computer science, engineering, or a related field, or equivalent practical experience
• A Google Cloud certification is a strong differentiator at application; if you don't hold one yet, obtaining one within the first two months is required, with exam sponsorship and prep time provided. The preferred certification is Google Cloud Professional Machine Learning Engineer, covering Vertex AI, generative AI, and production ML

Nice to Have

• Experience with MCP servers, multi-agent patterns, or LLM evaluation tooling such as LangSmith, Langfuse, or promptfoo
• Experience with Terraform or CI/CD pipelines
• Experience with GCP, BigQuery, or Google Workspace integrations alongside Gemini Enterprise

Work Schedule

• 100% remote setup so you can work wherever you're most productive
• This position operates on a full-time basis, with dedicated hours to ensure alignment with the team and delivery of quality work
• Availability during US business hours

Compensation & Time Off

• Compensation paid in USD
• Paid bi-monthly on the 15th and 30th
• Paid Time Off according to company policy
• Holidays observed according to company guidelines

Application Requirements

Please submit:

• An updated resume
• A GitHub link or portfolio showing AI systems or full-stack projects you’ve built and shipped in production, with a focus on the Google AI stack or agentic work
• A 1-2 minute Loom video introducing yourself, walking through one production AI system you owned end to end on the Google stack, and explaining how you approached evaluation and reliability alongside the feature build

Only candidates who submit both a portfolio and Loom video will be moved to the next step of the hiring process.