Senior AI Platform Engineer (LLM & Agentic Systems)

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior AI Platform Engineer (LLM & Agentic Systems) based in Brazil. This role sits at the intersection of advanced AI engineering and production-grade backend systems, focused on building intelligent platforms powered by large language models and agentic architectures. You will join a highly technical environment where the mission is to transform complex, unstructured data into reliable, scalable, and actionable AI-driven systems used in real-world enterprise contexts. The position involves designing and implementing multi-agent workflows, retrieval-augmented generation pipelines, and robust AI orchestration frameworks. You will contribute to systems that combine LLM reasoning with deterministic software engineering to ensure accuracy, stability, and performance at scale. The environment is fast-paced, deeply technical, and oriented toward solving meaningful problems with cutting-edge AI technologies. This is a hands-on engineering role where your decisions will directly shape the architecture and evolution of next-generation AI platforms. Accountabilities: Design and build advanced agentic AI systems, including multi-agent workflows, orchestration frameworks, and tool-calling infrastructures that enable LLMs to interact with external systems. Develop and optimize RAG pipelines, including embedding strategies, vector databases, hybrid search, reranking, and scalable knowledge ingestion systems. Build robust AI application backends using Python and modern frameworks such as FastAPI, ensuring performance, scalability, and maintainability. Implement structured output systems and validation layers using schema-driven approaches (e.g., Pydantic, JSON Schema) to ensure reliable AI responses. Design evaluation, testing, and monitoring systems for AI applications, including benchmarking, regression testing, and A/B testing for model and prompt performance. Optimize LLM performance across latency, cost, and quality by refining prompts, caching strategies, and model selection approaches. Collaborate on production deployment using containerized environments (Docker, Kubernetes) and support full lifecycle delivery from design to operations. Requirements: 4+ years of software engineering experience, including at least 2+ years building production AI or LLM-powered applications. Strong Python expertise with experience building scalable backend systems using FastAPI or similar asynchronous frameworks. Proven experience with agentic frameworks such as LangGraph, LangChain, or custom orchestration solutions. Hands-on experience designing and deploying RAG architectures with vector databases such as Pinecone, Weaviate, Qdrant, FAISS, or pgvector. Strong understanding of prompt engineering, structured outputs, LLM optimization, and schema-driven development using Pydantic. Solid knowledge of PostgreSQL, Redis, and distributed system design principles. Experience building observability, evaluation, and testing frameworks for AI-driven applications. Strong API design skills, with understanding of WebSockets, backend architecture, and system debugging. Benefits: Competitive compensation aligned with senior-level AI engineering roles Remote-first work model within Brazil Opportunity to work on cutting-edge agentic AI and LLM systems in production environments High-impact role with direct influence on architecture and technical strategy Exposure to modern AI stack including LLMs, RAG, vector databases, and distributed systems Collaborative environment with experienced AI and software engineering teams Strong focus on innovation, engineering excellence, and continuous learning How Jobgether works: We use an AI-powered matching process to ensure your application is reviewed quickly, objectively, and fairly against the role's core requirements. Our system identifies the top-fitting candidates, and this shortlist is then shared directly with the hiring company. The final decision and next steps (interviews, assessments) are managed by their internal team. We appreciate your interest and wish you the best! Why Apply Through Jobgether? Data Privacy Notice: By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR). You may exercise your rights (access, rectification, erasure, objection) at any time. #LI-CL1