Engenheiro(a) de IA Sr. in Brazil at Jobgether
Job Description
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for an Engenheiro(a) de IA Sr. based in Brazil.
We are seeking a Senior AI Engineer to build and maintain the technical infrastructure powering AI models and intelligent agents in a production environment within the financial sector. In this role, you will own the journey from experimentation to deployment, ensuring that AI solutions are reliable, secure, observable, and scalable. You will develop advanced applications using Retrieval-Augmented Generation (RAG), large language models, and autonomous agents integrated with enterprise data and transactional systems. Combining software engineering expertise with MLOps and LLMOps practices, you will establish robust deployment pipelines, monitoring capabilities, and operational controls. This is an opportunity to work on complex AI initiatives in a regulated environment, helping transform innovative concepts into dependable, production-ready solutions.
Build and maintain end-to-end deployment pipelines, including version control, automated testing, controlled releases, and rollback procedures.
Implement and manage MLOps practices, including model registries, training and inference pipelines, automated retraining, monitoring, and model drift detection.
Develop LLMOps capabilities such as unified model gateways, prompt versioning, automated evaluation, and caching mechanisms.
Design and build RAG-based applications and AI agents, including agent execution harnesses, context management, skills, tools, and execution controls.
Integrate AI solutions with enterprise data sources, APIs, and transactional systems, including integrations through the Model Context Protocol (MCP).
Monitor and optimize system quality, availability, latency, throughput, and operational costs, ensuring traceability at the usage level.
Implement AI security measures, guardrails, access controls, and data protection mechanisms in accordance with regulated-environment requirements.
Investigate production incidents, troubleshoot failures, and maintain recovery procedures and operational documentation.
Ensure the reliability, reproducibility, security, and observability of AI models and agent-based applications throughout their lifecycle.
Professional experience in software engineering applied to data systems and artificial intelligence.
Strong proficiency in Python and practical experience with Apache Spark.
Hands-on experience implementing MLOps and LLMOps architectures and workflows.
Understanding of agent execution harnesses, including execution cycles, state management, checkpoints, recovery, and failure handling.
Knowledge of context engineering, including information selection, memory management, token limits, and isolation between sessions and users.
Experience implementing agent skills, tool calling, and MCP integrations to provide agents with access to tools and capabilities.
Practical knowledge of Retrieval-Augmented Generation (RAG), embeddings, information retrieval, and context relevance evaluation.
Experience with cloud platforms, containerization, CI/CD pipelines, and infrastructure as code.
Strong understanding of production performance factors, including latency, throughput, cost per request, and system failure scenarios.
Knowledge of AI security practices, including guardrails, permissions, secrets management, and protection against prompt injection.
Experience working in regulated environments with strict auditability, compliance, and traceability requirements.
Nice to have: Experience in financial services; familiarity with vector databases and model-serving platforms; experience with multi-agent orchestration and frameworks such as LangGraph and LangChain; and knowledge of FinOps practices applied to AI consumption.
Fully remote work arrangement.
Full-time engagement under a contractor (PJ) arrangement.
Opportunity to work on advanced AI engineering initiatives in the financial services sector.
Exposure to production-scale AI platforms, LLMOps, MLOps, RAG, and intelligent agent architectures.
Opportunity to contribute to the architecture and evolution of secure, scalable, and reliable AI solutions.
Scan to Apply
Just scan this QR code to apply from your phone.
- Fast
- Easy
- Apply on the go