We are looking for a Senior AI/LLM Engineer to work on the development, operation, and evolution of advanced solutions based on language models, RAG, agents, and distributed architectures.
Requirements
- Design, develop, and operate AI/LLM solutions in production (chatbots, agents, and RAG pipelines).
- Build data and embeddings pipelines, perform indexing, vector optimization, and re-ranking implementation.
- Implement guardrails, LLM/RAG evaluation, and quality, cost, and latency monitoring.
- Orchestrate services in AWS, Azure, and/or GCP using IaC, CI/CD, containers, and Kubernetes.
- Collaborate with Product, Security, and Data teams to ensure quality, compliance (LGPD), and business impact.
- Work with the Architecture team to define standards and best practices for generative AI.
- Develop APIs, microservices, and event-driven architectures to support AI-based solutions.