AI Engineer – GenAI Platform, Mid-Level

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

📋 Description

• Design and create services focused on Generative AI and multi-agent systems.

• Execute retrieval-augmented generation (RAG), tool invocation, and agent orchestration solutions.

• Integrate and manage models via large language model (LLM) gateways.

• Establish practices for LLM operations, including monitoring, observability, and governance.

• Implement mechanisms for consumption measurement, chargeback, and optimizing inference costs.

• Develop and sustain data pipelines that facilitate billing and metering processes.

• Employ MLOps, continuous integration/continuous deployment (CI/CD), automated testing, and model lifecycle management methodologies.

• Manage incidents, monitor system reliability, and drive continuous service improvement.

• Work collaboratively with global teams across Product, Engineering, Platform, Security, and Data.

⛳️ Requirements

• Candidates must be based in Brazil.

• Experience in Software Engineering and Applied AI is essential.

• Proven track record of delivering Generative AI projects in production settings.

• Advanced proficiency in English is required.

• Familiarity with Generative AI and Agentic AI concepts.

• Understanding of multi-agent orchestration, tool invocation, multi-step reasoning, RAG, and prompt engineering.

• Experience with frameworks such as LangChain, LangGraph, or their equivalents.

• Knowledge of LLM operations and LLM platforms.

• Experience with LLM gateways like LiteLLM or comparable technologies.

• Proficient in model integration through APIs.

• Knowledge in observability and assessment of LLM-based applications.

• Understanding of latency and performance enhancement techniques.

• Familiarity with vector databases and retrieval mechanisms.

• Advanced skills in Python programming.

• AWS knowledge is preferred.

• Strong practices in architecture, observability, and reproducibility.

• Knowledge of MLOps, including versioning, experiment tracking, CI/CD, automated testing, deployment, and rollback of AI services.

• Familiarity with batch and streaming data pipelines, Spark, Lakehouse architectures, and data orchestration.

• Experience with Kafka and event streaming, Terraform and Infrastructure as Code, Databricks (Delta Lake and DLT), internal developer platforms, and global, distributed environments are advantageous.

🏝️ Benefits

• Equal opportunity and affirmative action employer.

• Commitment to inclusive recruitment initiatives.

• Opportunities for professional development.

• Affinity groups supporting underrepresented communities: ExperianPride, Ubuntu, Women in Experian, Aspire, and Connecting Generations.