Senior ML/AI Engineer | Remote - 135807 INT (Alphaville - Barueri, BR, 06.

What we're looking for: We are looking for an experienced Senior ML/AI Engineer to work on the development and architecture of advanced machine learning and generative AI systems. The candidate will be responsible for the design, construction, and deployment of complex agent-based AI systems, providing technical guidance and collaborating with teams to define the AI roadmap. Responsibilities: • Design, build, and deploy complex agent-based AI systems; • Provide technical guidance to junior team members; • Collaborate with production and application teams to define the AI roadmap; • Design and implement agentic AI systems, including tool-calling agents, structured reasoning, and secure action execution, while defining security and compliance guidelines; • Lead the development of evaluation frameworks for LLMs, designing retrieval pipelines, prompt synthesis, response validation, and self-correction loops; • Architect connections between agents and observability, incident management, and deployment systems for automated diagnostics and runbook execution; • Collaborate with production and application teams to translate challenges into agentic AI roadmaps, defining objective functions related to reliability, risk reduction, and cost reduction; • Design validation models, adversarial prompts, and policy checks, establishing fallback and rollback strategies, and implementing continuous assessments; • Optimize costs and latency through prompt engineering, context management, caching, model routing, and distillation to meet SLOs; • Mentor and review the work of junior and mid-level engineers in agent design, evaluation methodology, and production readiness. Requirements and Qualifications: • In-depth experience with AWS services (ECS/EKS, Lambda, S3, DynamoDB, Redshift, Step Functions, SageMaker) and infrastructure as code (Terraform/CloudFormation); • Experience in software development with Python, C/C++, Go, or Java, with strong experience in large-scale Python; • Experience in the design, architecture, testing, and deployment of ML systems in production (deployment, evaluation, monitoring, data pipelines, fine-tuning workflows); • In-depth hands-on experience with LLMs, including API integration, prompt engineering, fine-tuning/adaptation, RAG, and tool-using agents; • Strong understanding of commercial and open-source LLMs and their trade-offs (e.g., OpenAI, Gemini, Llama, Qwen, Claude); • Advanced knowledge of applied statistics, fundamental ML concepts, algorithms, and data structures; • Advanced/fluent English.