5 months ago
São Paulo, Brazil or Bogotá, ColombiaSenior
Responsibilities
- Build and deploy scalable LLM-powered AI products for Yuno’s payment orchestration platform.
- Design, test, optimize, and refine prompts based on model outputs, feedback loops, and user interaction data.
- Develop AI use cases for customer service, fraud prevention, and payment assistance.
- Integrate AI solutions with payment systems, core services, RESTful APIs, and third-party platforms.
- Research emerging LLM and prompt-engineering technologies and identify product innovation opportunities.
- Use payment and user interaction data to fine-tune models and improve product performance while following data privacy and AI ethics practices.
Requirements
- Extensive experience building and deploying products using LLMs such as GPT or similar models.
- Expertise in prompt engineering, including designing, testing, and optimizing prompts.
- Strong programming experience with Python and frameworks such as TensorFlow or PyTorch.
- Experience integrating AI solutions with RESTful APIs and third-party platforms.
- Hands-on experience with vector databases such as Pinecone, Weaviate, or FAISS.
- Familiarity with speech-to-text and text-to-speech tools such as Whisper, AWS Polly, or Google Speech-to-Text.
- Experience developing and deploying scalable AI systems in cloud environments such as AWS, GCP, or Azure.
- Fluent English and strong problem-solving skills.
- Preferred: familiarity with Hugging Face or OpenAI APIs, plus strong analytical and data visualization skills.
Benefits
- Remote work from anywhere.
- One-time home office allowance.
- Work equipment.
- Stock options.
- Health plan wherever the employee is located.
- Flexible days off.
- Language, professional, and personal growth courses.
Tech Stack
Categories
