AI Analyst & Prompt Engineering Specialist

Teleperformance (TP) is a global digital business services company with a local presence in Santo Domingo. Our mission is to provide advanced, digitally-powered business services that streamline operations for the world's top brands while contributing to the betterment of our communities and the environment.Role DescriptionWe are seeking an analytical, detail-driven AI Analyst & Prompt Engineering Specialist, this role operates at the intersection of business intelligence and advanced LLM behavior. The specialist will support rapid experimentation inside the TP AI Playground, turning ideas into working prototypes through structured prompting, rigorous evaluation, and cross-team collaboration.You will shape how AI systems interpret instructions, interface with enterprise systems, and deliver measurable business outcomes. This role requires someone who is both analytical and creative, capable of designing effective prompts while also validating outputs through data-driven methodologies.The AI Analyst & Prompt Engineering Specialist will contribute to the full lifecycle of AI solution development from early discovery and dataset exploration to tuning prompts, evaluating outputs, and supporting deployment.The role provides technical and analytical expertise to ensure that LLM-powered solutions deliver consistent, safe, and high-quality results. The specialist will collaborate with engineering, business units, and the Solutions Lab to ensure AI applications align with business needs and measurable KPIs.Responsibilities• Design, refine, and maintain high quality prompt libraries used across agentic workflows, prototypes, and enterprise AI solutions. • Build prompt architectures including few shot prompting, chain of thought, tool calling schemas, and multi-step prompt chains. • Conduct A/B testing and comparative evaluations across multiple foundation models (GPT 4o, Claude 3.5, Gemini 1.5, Llama, Mistral) to determine the best model fit per use case. • Evaluate AI output quality using measurable frameworks (accuracy, hallucination rate, bias, toxicity, latency, token cost, ROI). • Analyze datasets of AI interactions to identify failure patterns, optimize instructions, and improve model reliability. • Collaborate with developers and platform engineers to integrate prompts into production-ready AI agents, microservices, and SaaS workflows. • Support the implementation of RAG (Retrieval Augmented Generation) strategies in collaboration with the engineering team. • Establish guardrails, safety layers, and governance guidelines to ensure compliance with data privacy, security, and ethical requirements. • Work within the TP AI Playground/Sandbox to rapidly experiment, validate concepts, and convert ideas into functional prototypes. • Document prompt behavior, expected outputs, evaluation criteria, and performance changes across iterations. • Maintain a “fail fast, learn faster” mindset, delivering continuous improvement cycles in weeks, not months. • Partner with Compliance/Legal to ensure AI interactions follow SOC2, GDPR, and internal data-handling standards.Qualifications• Bachelor’s degree in computer science, Data Analytics, Information Systems, or related field. • Training in LLM fundamentals, Responsible AI, or Prompt Engineering (preferred).• Advanced degree is a plus.• 2+ years working with LLM-based applications, AI analysis, or business intelligence. • Experience designing and evaluating prompts in production or prototype environments. • Prior work with model evaluation, A/B testing, or data-driven decision-making frameworks. • Exposure to enterprise workflows, SaaS ecosystems, or digital transformation initiatives.• Be recommended by your manager.• Minimum 1 year tenure in current position.• No unjustified absences for the last 6 months.• No Warnings for the last 6 months.Special Certifications• Hands-on experience with LLM APIs (OpenAI, Anthropic, Azure OpenAI, Gemini). • Familiarity with structured prompting, tool/function calling, and evaluation frameworks. • Knowledge of LangChain, LlamaIndex, or similar orchestration frameworks. • Experience with SQL and vector databases (Pinecone, Weaviate, ChromaDB). • Understanding of REST APIs, JSON, and client/server interactions.Technical Skills• Strong understanding of LLM behavior, prompt engineering patterns, and evaluation metrics. • Proficiency in Python; familiarity with JavaScript/Node.js is a plus. • Experience working with tokenization, embeddings, and model performance metrics (token cost, latency, throughput). • Understanding of RAG architecture and document retrieval concepts. • Ability to analyze datasets, identify patterns, and recommend improvements. • Comfortable working with cloud-based AI platforms (Azure AI Studio, AWS Bedrock, Google Vertex AI).• English Level: C1 or B2. Competencies and Specific Skills• Excellent communication skills, able to translate complex AI behavior into actionable insights. • Strong analytical and problem-solving abilities. • Highly collaborative, able to partner across technical and business teams. • High degree of integrity, confidentiality, and ownership. • Ability to work in rapidly changing environments with tight iterative cycles.• Process Excellence• AI Proficiency• Data Literacy• Emotional Intelligence• Open Mindedness• Critical Thinking• Solution OrientationWhat We Offer:• Competitive compensation and benefits package.• Opportunities for professional development and career growth.• A dynamic and collaborative work environment.