We are looking for an innovative AI/Agentic Systems Engineer to integrate OpenAI’s GPT and other NLP models into our platform, ensuring effective brief clarification and action point generation. This role will also focus on developing autonomous agent architectures, including decision-making frameworks, goal planning, and multi-agent interactions. The ideal candidate is passionate about AI, automation, and building intelligent systems that enhance productivity and decision-making.

➡️ This position is Full-Time (Remote in Brazil)

Responsibilities

• Design and implement autonomous agent architectures for decision-making, including tools like OpenAI’s functions and reinforcement learning frameworks.
• Develop and integrate multi-agent systems for collaboration and task distribution.
• Research and apply goal-setting, planning, and execution frameworks (e.g., hierarchical reinforcement learning).
• Fine-tune AI models for contextual understanding, intent inference, and action generation.
• Ensure safe and interpretable decision-making by implementing explainable AI (XAI) methods.
• Collaborate with backend developers to integrate agentic capabilities into workflows.
• Integrate AI/LLM capabilities (e.g., OpenAI GPT) into our platform for brief clarification and summarization.
• Develop and fine-tune natural language processing (NLP) algorithms to understand client requests.
• Build recommendation systems for ticket assignment and team performance analytics.
• Train and optimize machine learning models for specific tasks like brief generation.
• Monitor and improve the accuracy and performance of AI features.

Requirements

• Expertise in reinforcement learning frameworks (e.g., OpenAI Gym, Stable-Baselines3, Ray RLlib).
• Proficiency with multi-agent systems and algorithms (e.g., distributed coordination).
• Strong understanding of planning algorithms (e.g., Monte Carlo Tree Search, A*).
• Experience with explainable AI (XAI) frameworks and ethical AI design principles.
• Knowledge of NLP and task-based dialogue systems (fine-tuning LLMs for task execution).
• Strong programming skills in Python and familiarity with cloud-based model deployment.
• Strong experience with NLP libraries and frameworks (spaCy, NLTK, Hugging Face).
• Understanding of AI ethics, bias reduction, and data privacy concerns.
• Strong problem-solving skills and the ability to work collaboratively.