Senior Deployed AI Engineer – Gemini

This is a fully remote position, open to applicants in Argentina, +2 more countries.

📋 Description

• Create user-facing interfaces using TypeScript and React, along with backend services and APIs in Python or Node.

• Implement agentic functionalities, including orchestration, tool and function invocation, memory management, and guardrails.

• Develop retrieval-augmented generation pipelines that encompass ingestion, chunking, embeddings, and both vector and hybrid searches.

• Design and construct agents utilizing Gemini models, Vertex AI, the Agent Development Kit, and the Agent Engine.

• Set up and configure Gemini Enterprise for clients, which includes the Agent Designer, an Inbox for managing long-running agents, and agent sandboxes.

• Integrate Gemini Enterprise with client application ecosystems through first-party and partner connectors while ensuring permissions, governance, and auditability.

• Construct grounded, retrieval-supported applications utilizing Vertex AI Search, RAG Engine, grounding techniques with Google Search, and BigQuery.

• Implement agent interoperability via the A2A protocol and MCP.

• Keep track of Google's releases and convert new capabilities into client value.

• Develop evaluation suites and regression tests for LLM-powered features.

• Monitor production cost, latency, and quality.

• Deploy applications on GCP, Azure, or AWS.

• Build and maintain data pipelines that support AI systems.

• Regularly use Claude Code, Gemini CLI, Codex, or Cursor with verification and review.

• Communicate updates, trade-offs, and obstacles to clients and project leads.

• Assist with pre-sales activities as necessary.

• Provide mentorship to junior engineers.

• Contribute to internal accelerators, reusable components, and engineering standards.

⛳️ Requirements

• 3 to 5 years of experience in software or data engineering.

• Significant hands-on experience with AI tools and LLM-based development in the past year.

• Strong practical experience with the Google AI stack, including Gemini models and Vertex AI.

• At least one solution successfully deployed in production on GCP.

• Proficient programming skills in Python and TypeScript or JavaScript.

• Experience in building and consuming APIs.

• Background in front-end development using React or similar frameworks.

• Familiarity with at least one backend framework.

• Direct experience with RAG, embeddings, and vector search.

• Experience with at least one agentic framework such as Google ADK, LangGraph, or LangChain.

• Strong working knowledge of GCP; experience with Azure or AWS is advantageous.

• Proficient with Claude Code, Gemini CLI, Codex, or Cursor.

• Experience in building and maintaining data pipelines.

• Professional proficiency in English at a minimum of C1 or C2 level.

• Bachelor's or Master's degree in computer science, engineering, or a related field, or equivalent practical experience.

• Google Cloud certification is mandatory within the first two months if not already obtained.

• Preferred certification: Google Cloud Professional Machine Learning Engineer.

• Experience with MCP servers, multi-agent patterns, or LLM evaluation tools is a plus.

• Familiarity with Terraform or CI/CD pipelines is beneficial.

• Experience with GCP, BigQuery, or Google Workspace integrations alongside Gemini Enterprise is a plus.

• Availability during US business hours.

• An updated resume.

• A GitHub link or portfolio showcasing AI systems or full-stack projects that have been built and deployed in production.

• A 1–2 minute Loom video introducing yourself and demonstrating one AI system you have owned end-to-end in production.

• The portfolio and Loom video are both required to proceed to the next stage of the hiring process.

🏝️ Benefits

• Paid Time Off in accordance with company policy.

• Holidays observed as per company guidelines.

• Compensation provided in USD.

• Payments made bi-monthly on the 15th and 30th.

• Sponsorship for exams and prep time for obtaining a Google Cloud certification.

• Fully remote work setup.

• Dedicated full-time hours for team alignment and quality delivery.