Prompt Designer

Role DescriptionA Prompt Designer is responsible for designing, testing, refining, and documenting prompts and instruction frameworks that guide artificial intelligence and large language models to produce accurate, relevant, consistent, and useful outputs. The role combines language design, user intent analysis, AI behavior evaluation, structured reasoning, and experimentation to improve AI-powered products, workflows, and applications.Key responsibilities include designing clear and effective prompts for conversational AI, generative AI, content-generation systems, automation workflows, and enterprise AI applications; translating business requirements, user needs, and product objectives into structured prompt specifications; developing reusable prompt templates, system instructions, examples, constraints, variables, and response formats; testing prompts across different models, datasets, scenarios, and user inputs; evaluating AI outputs for accuracy, relevance, consistency, reasoning quality, tone, safety, and adherence to requirements; identifying hallucinations, ambiguity, bias, inconsistencies, formatting errors, and unwanted model behavior; iteratively refining prompts through experimentation and performance analysis; developing prompt libraries, version-control processes, evaluation frameworks, and documentation standards; designing structured outputs such as JSON, tables, classifications, summaries, extraction formats, and workflow responses; working with AI engineers, machine-learning engineers, software developers, product managers, UX designers, data scientists, researchers, and business stakeholders; supporting Retrieval-Augmented Generation (RAG), AI agents, tool-calling, workflow automation, and multi-step AI applications; creating evaluation datasets, test cases, benchmarks, and quality criteria for prompt performance; analyzing model behavior and comparing outputs across different prompting techniques and model configurations; using Python, APIs, AI development platforms, testing frameworks, and analytics tools where appropriate; applying techniques such as few-shot prompting, chain-of-thought alternatives, structured prompting, role-based instructions, context engineering, prompt chaining, and output validation; monitoring changes in model behavior following model updates, configuration changes, or knowledge-base modifications; supporting responsible AI practices by considering privacy, security, fairness, safety, and compliance requirements; identifying opportunities to automate repetitive tasks using AI; preparing prompt documentation, experiment reports, evaluation results, and implementation guidelines; and continuously improving AI workflows, prompt quality, model reliability, user experience, and business outcomes.QualificationsBachelor's or Master's degree in Computer Science, Artificial Intelligence, Data Science, Linguistics, Computational Linguistics, Information Technology, Human-Computer Interaction, or a related discipline.Strong understanding of generative AI, large language models, natural language processing, and conversational AI.Strong ability to write clear, precise, structured, and context-aware instructions.Excellent analytical, critical-thinking, problem-solving, writing, and communication skills.Understanding of prompt engineering, prompt evaluation, few-shot prompting, structured prompting, context engineering, and output validation.Familiarity with AI models, APIs, model parameters, embeddings, vector databases, RAG, AI agents, function calling, and automated AI workflows is advantageous.Knowledge of Python, JavaScript, APIs, JSON, SQL, or other technical tools is beneficial.Familiarity with AI platforms, LLM evaluation frameworks, prompt-management tools, and experimentation environments.Strong ability to analyze AI-generated outputs and identify hallucinations, inconsistencies, ambiguity, bias, formatting issues, and instruction-following failures.Understanding of data privacy, AI safety, responsible AI, security, and governance principles.Ability to collaborate effectively with AI engineers, developers, product managers, designers, data scientists, researchers, and business stakeholders.Strong documentation and version-control practices for prompt libraries, experiments, evaluation datasets, and AI workflows.Familiarity with automated testing, benchmarking, A/B testing, quality metrics, and model evaluation is advantageous.Knowledge of retrieval systems, knowledge bases, semantic search, vector databases, and enterprise AI applications is beneficial.Strong creativity and experimentation skills combined with a systematic, data-driven approach to problem solving.Ability to manage multiple AI projects, use cases, testing scenarios, and optimization initiatives.Strong attention to detail and ability to balance user experience, technical requirements, model limitations, and business objectives.Relevant AI, machine-learning, NLP, cloud, or technical certifications are advantageous.Strong commitment to continuous learning and staying informed about LLMs, multimodal AI, AI agents, RAG, model evaluation, automation, and emerging generative-AI technologies.