Especialista II – Engenheiro de IA, Tech Demanda e Operações

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

📋 Description

• The Demand Planning team at Grupo Boticário aims to enhance production accuracy through a multidisciplinary structure that evolves from statistical models to an autonomous platform, where AI acts as the strategic co-pilot of the business.

• Design and implement Multi-Cloud AI Agent architectures: You will be responsible for the technical design and implementation of autonomous agents operating within our Modern Hybrid Mesh architecture. You will orchestrate rapid inference models (such as Claude 3.5 Sonnet and DeepSeek-R1) via Amazon Bedrock for real-time screen interactions, and deep reasoning models (like Gemini 3 Pro) on GCP Vertex AI for batch analysis with context windows of up to 1 million tokens.

• Context Engineering and Advanced RAG: Design and optimize Retrieval-Augmented Generation (RAG) pipelines using Amazon Bedrock Knowledge Bases. Implement intelligent extraction techniques and dynamic metadata filtering to ensure agents accurately retrieve the company's stock policies and lead times.

• Develop the reasoning capability of the Agents: Create interactive co-pilots for demand planning using the Thought Signatures pattern to maintain the AI's reasoning cohesion in complex flows, ensuring deterministic and auditable responses from structured data (Iceberg/RDS).

• Asynchronous Integration and Orchestration: Develop secure communication between AI agents and our Kotlin microservices. For long-running tasks, you will integrate agent flows with AWS Step Functions using the Callback pattern, eliminating idle times and ensuring fault tolerance.

• Work on the productization of AI solutions (LLMOps and Security): Ensure governance, cost monitoring of inference, and application security. Implement Guardrails in Bedrock and configure Cross-Cloud access using Workload Identity Federation (WIF) for secure communication between AWS and GCP without static credential traffic.

• Collaboration and technical development: Actively collaborate with the Modeling Squad and the Application Squad, translating outputs from predictive statistical models (ARIMA/XGBoost) into textual insights and automated action suggestions for Supply Chain users.

⛳️ Requirements

• Strong experience in Generative AI: Proven hands-on experience in the architecture, deployment, and productization of complex applications using cutting-edge LLMs in mission-critical environments.

• Deep knowledge of Python and Agent Frameworks: Advanced proficiency in Python and mastery of agent building ecosystems and LLM orchestration (e.g., LangChain, LlamaIndex, Amazon Bedrock AgentCore, Vertex AI Agent Builder).

• Experience with Multi-Cloud AI: Familiarity with at least one of the major managed AI providers (AWS Bedrock or Google Vertex AI) and a deep understanding of the differences between real-time and batch inference.

• RAG Architecture and Vector Databases: Solid experience in semantic chunking, embedding models (e.g., Titan Multimodal), and search optimization in vector databases (e.g., OpenSearch, pgvector, Pinecone).

• Technical capability and critical thinking: Ability to make autonomous architectural decisions (e.g., when to use fine-tuning vs. RAG vs. complex Prompt Engineering) aimed at optimizing latency and cost per token.

• Advantage: Practical experience with the implementation of Workload Identity Federation (WIF) across clouds.

• Prior knowledge of the AWS Serverless ecosystem (Step Functions, Lambda, EventBridge).

• Understanding of Supply Chain business rules, Demand Planning (S&OP/IBP), or Finance.

• Experience with the Google BigLake platform and federated access to data in Apache Iceberg format.

• Familiarity with Kotlin or Java to facilitate integration with the Backend team (Rules Engine).

🏝️ Benefits

• Your health is a priority here.

• Medical and dental plan.

• Medication assistance.

• Health allowance for family members.

• Free psychotherapy sessions.

• Telemedicine and second medical opinion.

• Free flu vaccine.

• Health care programs.

• To support your nutrition.

• Meal voucher or local restaurant access (based on work model).

• Food allowance.

• Christmas food allowance.

• Ensuring well-being and quality of life in all aspects.

• Gym and physical activity studio plan.

• Home office assistance (for hybrid and remote work models).

• Health plan for pets.

• Day off on your birthday.

• Discounts of up to 40% on our products.

• Employee association (benefits and partnerships, multi-brand store, total pass gyms, courses, and more!).

• Travel and accommodation programs.

• For the family, our most precious asset.

• Child education assistance.

• Child nutrition credit.

• Babysitter assistance.

• School material assistance.

• Legal, psychological, and social guidance.

• Support for atypical parents.

• Extended parental leave (180 days for mothers and 120 days for fathers).

• Mobility for your on-site journey.

• Transportation and parking allowance (for hybrid and on-site models).

• Security for financial protection and peace of mind.

• Life insurance.

• Support for the passing of parents.

• Private pension.

• Payroll loans.