AI Engineering – Specialist

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

📋 Description

• Create comprehensive Generative AI solutions, overseeing everything from technical design to deployment and ongoing operations.

• Take the lead or provide support in developing copilots, automation tools, and assistants for both clients and internal teams, ensuring they meet quality, security, and scalability standards.

• Enhance the LLMOps platform with a focus on governance, traceability, observability, cost management, and security.

• Collaborate effectively with architecture, engineering, product, and operations teams to define and implement impactful business solutions.

• Establish and communicate CI/CD best practices for Generative AI applications in both on-premises and cloud settings.

• Analyze and resolve production failures and incidents, conduct root cause analyses, and recommend structural improvements.

• Advocate for technical best practices, conduct code reviews, standardize solutions, and disseminate knowledge across various teams.

⛳️ Requirements

• Proven experience with Generative AI, LLMs, embeddings, and natural language processing techniques.

• Strong proficiency in Python and familiarity with libraries/frameworks such as LangChain, Transformers, or their equivalents.

• Extensive experience with RAG architectures, including techniques like re-ranking, dynamic chunking, and context-aware retrieval.

• Solid understanding of Git and both relational and non-relational databases.

• Experience in Data Science applied to unstructured data.

• Practical experience with LLMOps, encompassing pipelines, versioning, monitoring, evaluation, and model cost management.

• Familiarity with open-source models such as Mistral, LLaMA, Mixtral, and Phi.

• Experience with autonomous agents or orchestration of workflows using LangGraph or similar tools.

• Awareness of emerging protocols and standards like MCP and A2A.

🏝️ Benefits

•