Senior AI Engineer (LLMs & Agentic AI)

New

JobgetherArtificial intelligence

Based in BrazilFull-TimeSenior

Salary not disclosed

Apply NowOpens the employer's application page

Job Details

Languages: Professional English proficiency sufficient to participate in technical interviews, explain complex implementation details, and sustain in-depth technical discussions with precision.
Experience: Senior-level experience
Required Skills: PythonSQLPrompt Engineering

Have senior-level experience building and deploying production AI applications using Python and LLM technologies.
Demonstrate strong proficiency in Python and software engineering principles for maintainable production systems.
Have strong SQL skills and practical experience with cloud data warehouses.
Bring hands-on experience developing production-grade LLM and agentic AI applications.
Have personally designed and built an MCP server, not only integrated with or consumed an existing server.
Have experience with tool calling, context management, multi-step orchestration, and agentic workflows.
Have practical experience integrating hosted LLM APIs, particularly Anthropic and OpenAI, into production applications.
Know prompt engineering, prompt versioning, fallback mechanisms, and approaches to optimizing model cost, latency, and performance.
Have experience with conversational AI, intent classification and routing systems, or multi-API orchestration workflows.
Have experience developing LLM evaluation methodologies and frameworks.
Be able to work effectively within partially documented or brownfield codebases.
Have professional English proficiency for technical interviews and in-depth technical discussions.
A bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related field is preferred; equivalent professional experience is acceptable.

Build, maintain, and enhance MCP servers, tool definitions, and context management capabilities.
Design intent classification, evaluation, and routing workflows for natural language applications.
Develop multi-step orchestration workflows coordinating tools, APIs, and data sources.
Integrate hosted LLMs, including Anthropic and OpenAI, into production environments.
Manage prompt engineering, prompt versioning, fallback strategies, and optimization initiatives.
Develop and maintain LLM evaluation frameworks to measure model quality and production behavior.
Write and optimize SQL queries against cloud data warehouses for analysis, evaluation, and monitoring.
Support backend functionality for conversational interfaces and MCP-enabled applications.
Contribute to AI platform architecture and improve existing codebases, including partially documented legacy systems.

View Full Description & ApplyYou'll be redirected to the employer's site