About Us Pearl is AI for professional services at global scale, combining advanced AI with verified human expertise to deliver help that is accurate, accountable, and fast. Since 2003, our network has connected millions of customers with licensed professionals across 196 countries, making real expertise available anytime, anywhere. Our Values - Data driven: Data decides, not egos - Courageous: We take risks and challenge the status quo - Innovative: We're constantly learning, creating, and adapting - Lean: We focus on customers, using lean testing to learn how to serve them best - Humble: Past success is not a guarantee of future success About the Role We are seeking an AI Prompt Engineer II who combines strategic thinking, scientific expertise, and hands-on building skills. You will join a dynamic, agile team dedicated to designing, testing, and scaling large language model (LLM) prompts that drive impactful user experiences. Leveraging your deep knowledge of Generative AI, you will enhance our AI-powered expert platform, unlocking meaningful business outcomes and shaping how AI understands customers and supports experts. What You’ll Do - Design, build, and develop AI agents - Create complex multi-part prompting systems with parameter optimization and implement advanced prompting techniques - Develop comprehensive evaluation frameworks to measure performance across multiple dimensions, comparing approaches such as retrieval-augmented generation (RAG), fine-tuning, and advanced prompting methodologies - Analyze and optimize LLM performance using A/B testing, usage metrics, and strategic feedback loops - Develop AI-driven workflows that improve user interactions and Customer Care support - Design and refine expert playbooks to enhance knowledge sharing and operational efficiency - Run experiments to validate ideas rapidly and iterate based on performance data and user insights - Collaborate cross-functionally with product managers, engineers, and stakeholders to identify LLM opportunities and translate technical capabilities into business value - Manage stakeholder expectations and communicate complex technical concepts effectively to both technical and non-technical audiences - Implement LLMOps best practices including model governance, lifecycle management, and performance monitoring to ensure production-ready AI systems - Educate and empower internal teams to build better prompts and leverage AI tools effectively What We’re Looking For - Master’s or PhD in Computer Science, Computational Linguistics, Machine Learning, or a related field preferred - Strong proficiency in Python with hands-on experience building and testing complex prompting systems - Deep understanding of LLMs and advanced frameworks, with expertise across multiple LLM vendors and model versions - Proven experience developing and applying evaluation frameworks to test model outputs - Production experience with RAG and fine-tuning models - Demonstrated ability to automate large-scale API interactions and scripting for prompt testing, minimizing manual processes - Experience with LLMOps practices, including model governance, version control, performance monitoring, and lifecycle management - Strong stakeholder management skills and ability to collaborate effectively across technical and business teams - Proven track record of translating complex technical concepts into actionable business insights for diverse audiences - Analytical mindset with experience using Excel, Power BI, or Google Analytics - Solid understanding of NLP techniques - To build better prompts and leverage AI tools effectively - Excellent judgment with the ability to prioritize and independently drive projects forward while managing multiple stakeholder relationships - Experience working in agile, sprint-based development environments; familiarity with tools such as Azure Boards or Asana Our Commitment to an Inclusive Workplace We welcome people from all backgrounds who seek the opportunity to help build a future where professional services are readily available to all. If you have curiosity, passion, and a collaborative spirit, come work with us. Pearl is committed to an inclusive workplace. Pearl is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, disability, age, or other legally protected status. AI Disclosure & Informed Consent Artificial intelligence (AI) technology may be used during the hiring process to record, transcribe, analyze, and rank interview responses. By submitting your application and participating in the interview process, you acknowledge and consent to the use of AI technology in the hiring process. For more information see our AI Disclosure and Consent Policy. #LI-Remote

• Integrate LLMs and other GenAI models into web applications through efficient API design and implementation. • Build and optimize API endpoints to allow seamless, real-time interaction between front-end applications and back-end AI models. • Design and develop secure, scalable, and high-performing microservices for AI model deployment. • Develop robust back-end systems in Python to support the deployment, scalability, and maintenance of GenAI models. • Build and maintain data pipelines, including preprocessing data and post-processing AI model outputs for consumption by applications. • Use Kubernetes and Docker for containerization and orchestration to ensure scalable deployment and management of AI applications. • Implement continuous integration and continuous deployment (CI/CD) pipelines for automated testing and deployment of code changes. • Maintain a scalable and secure cloud infrastructure, leveraging platforms such as Google Cloud Platform, or Azure for model training, storage, and deployment. • Utilize vector databases (e.g., Pinecone, Weaviate, or Faiss) to manage and retrieve embeddings for efficient similarity search and recommendation systems. • Optimize and fine-tune LLMs to improve performance based on application needs.

• Architect and build full-stack, enterprise-grade platforms using reusable and modular agentic workflow patterns • Translate inputs from internal product teams into scalable, AI-powered workflows and services • Design and implement agentic workflows, including task decomposition and agent orchestration • Apply enterprise integration patterns to connect AI workflows with internal platforms and external systems • Guide and supervise coding assistants and AI agents to accelerate delivery • Design and operate event-driven architectures using AWS native services • Build secure Python back-end services for AI agents and enterprise integrations • Develop React-based front-end applications supporting complex user workflows • Build and operate multi-tenant architectures with security and compliance

• Build and deploy scalable AI products leveraging LLMs to support Yuno’s payment orchestration platform. • Develop and optimize prompts to ensure high-quality outputs from LLMs for specific use cases, such as customer service, fraud prevention, and payment assistance. • Design, test, and iterate prompts to achieve optimal performance for AI models. • Analyze and refine outputs based on feedback loops and user interaction data. • Collaborate with cross-functional teams to integrate AI features into existing payment systems and workflows. • Ensure seamless interaction between AI solutions and Yuno’s core services. • Stay updated on advancements in LLMs, prompt engineering, and related AI fields. • Experiment with emerging technologies to identify opportunities for Yuno’s product innovation. • Leverage payment and user interaction data to fine-tune AI models and improve product performance. • Ensure adherence to data privacy regulations and best practices in AI ethics.