Engenheiro(a) de Prompts / Desenvolvedor(a) de Agentes de IA
Accountabilities Design and configure system prompts, instructions, and conversational workflows for AI agents, adapting them to different use cases and LLM capabilities.
Evaluate and benchmark multiple LLM families, balancing response quality, cost, latency, and model-specific characteristics.
Build and refine AI agents within collaborative squads, including orchestration, tool usage, and context-memory management.
Define response-quality criteria and conduct structured, iterative testing to evaluate and improve AI-generated outputs.
Implement guardrails, out-of-scope response handling, and mitigation strategies for risks such as prompt injection.
Establish and document prompt engineering standards, versioning practices, reusable patterns, and best practices for broader team adoption.
Collaborate with technical teams to publish and maintain solutions through existing Git and CI/CD workflows.
Continuously investigate new AI platforms and techniques and adapt quickly to proprietary tools and evolving project requirements.
Requirements
Proven hands-on experience with prompt engineering in real-world projects using multiple LLM families, such as OpenAI/GPT, Anthropic/Claude, Google/Gemini, and Meta/Llama.
Practical experience developing AI agents within squads, including orchestration, tool integration, and context-memory management.
Experience defining metrics, test cases, and evaluation approaches for the quality and reliability of AI-generated responses.
Excellent Portuguese writing skills, with strong command of clarity, grammar, precision, tone, and the ability to create concise and effective instructions.
Familiarity with Git and existing CI/CD pipelines for version control and deployment.
Strong adaptability and willingness to learn and operate new proprietary AI platforms and technologies.
Ability to critically evaluate AI-generated content and iterate on prompts and workflows based on test results.
Strong collaboration, analytical thinking, attention to detail, and curiosity about emerging AI technologies.
Experience with RAG (Retrieval-Augmented Generation), particularly evaluating responses against documentary sources, is a plus.
Knowledge of Python for automating LLM testing and evaluation is a plus.
Experience handling sensitive data under LGPD requirements or working in healthcare environments is a plus.
Benefits
100% remote work.
Meal or food allowance.
Discounts on courses, universities, and language institutions.
Access to an online learning academy with free, regularly updated courses and certificates.
Mentoring opportunities.
Healthcare benefits and discounts for consultations and medical exams.
Dental assistance.
Employee discounts and benefits at participating establishments.
Travel benefits and discounts.
Pet benefits and assistance.
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