Prompt Engineer, AI at Herbalife Nutrition

Los Angeles, California, United States -

Full Time

Start Date

Immediate

Expiry Date

26 Jun, 26

Salary

0.0

Posted On

28 Mar, 26

Experience

5 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Prompt Engineering, Generative AI, LLMs, Prompt Design, Prompt Optimization, Prompt Chaining, RAG Systems, Adversarial Inputs Testing, Python Programming, LLM APIs, Vector Databases, Model Selection, A/B Testing, Few-Shot Learning, Chain-of-Thought, Ethical AI

Industry

Wellness and Fitness Services

Description

Overview THE ROLE: Unlock the full potential of large language models and generative AI by designing, refining, and scaling prompt strategies that produce accurate, reliable, and high-value AI outputs. In this role, you’ll sit at the intersection of human intent and machine intelligence, translating complex business needs into well-structured prompt frameworks that guide AI systems toward consistent, safe, and meaningful results. You’ll continuously experiment, optimize, and evolve prompts to improve model performance across real-world use cases. As an AI Prompt Engineer, you’ll blend technical understanding of AI behavior with creative problem-solving to build reusable, production-ready prompt patterns that power AI-driven solutions at scale — ensuring outputs meet quality, safety, and business standards. HOW YOU WOULD CONTRIBUTE: • Design and optimize prompts for large language models (LLMs) and generative AI systems to achieve specific business outcomes• Develop timely engineering frameworks and guidelines for different AI use cases and applications • Test and iterate on prompts systematically to improve accuracy, consistency, and output quality• Build prompt templates and libraries that enable reusable, scalable AI solutions across the organization• Implement prompt chaining and multi-step reasoning approaches for complex AI tasks• Design and optimize retrieval-augmented generation (RAG) systems combining prompts with knowledge bases• Evaluate AI model outputs against quality criteria and implement improvement strategies• Conduct prompt injection testing and implement safeguards against adversarial inputs• Collaborate with developers to integrate prompts into applications and workflows• Monitor production prompt performance and implement versioning and A/B testing strategies• Document prompt patterns, techniques, and findings for team knowledge sharing • Stay current with LLM capabilities, limitations, and best practices across different models• Provide guidance on prompt engineering to data scientists, developers, and business users• Analyze failure modes and edge cases, developing strategies to improve robustness• Implement ethical AI practices ensuring prompts produce fair, unbiased, and safe outputs• Make decisions on prompt strategies, model selection, and optimization approaches for AI applications Qualifications SKILLS AND BACKGROUND REQUIRED TO BE SUCCESSFUL: • 5+ years of experience in AI/ML, NLP, or software development with significant focus on working with LLMs and generative AI; demonstrated expertise in prompt engineering• Prompt engineering and prompt design for LLMs (GPT, Claude, Llama, etc.)• Understanding of transformer architectures and how LLMs process language• Natural language processing and computational linguistics• Systematic testing and experimentation methodologies• AI safety and responsible AI practices• Proven track record to craft prompts that consistently produce high-quality, reliable AI outputs• Deep understanding of LLM capabilities, limitations, and behaviors• Experience with various prompting techniques (few-shot learning, chain-of-thought, etc.)• Strong analytical skills to evaluate and improve prompt performance• Creative problem-solving to find innovative solutions using AI• Programming in Python for prompt automation and testing• Experience with LLM APIs (OpenAI, Anthropic, Azure OpenAI, etc.)• Knowledge of RAG architectures and vector databases• Understanding of fine-tuning and model customization• Familiarity with LLM evaluation frameworks and metrics• Experience with prompt management tools and platforms• Knowledge of conversational AI and chatbot design• Understanding of AI ethics, bias, and safety considerations Education • Minimum: Bachelor's degree in Computer Science, Computational Linguistics, Data Science, Artificial Intelligence, or related field• Preferred: Master's degree in AI, NLP, Computer Science, or related field; portfolio demonstrating successful prompt engineering projects• Certifications: AI/ML certifications, LLM-specific certifications, emerging prompt engineering certifications valuable• Equivalent Experience: 5+ years of hands-on experience working with LLMs and generative AI with proven track record of successful prompt engineering solutions may substitute for advanced degree #LI-AR1 #LI-REMOTE US Benefits Statement Herbalife offers a variety of benefits to eligible employees in the U.S. (limited to the 50 States and the District of Columbia), which includes Group Health Programs, other Voluntary Benefit Programs, and Paid Time Off. Group Health Programs include Medical, Dental, Vision, Health Savings Account (HSA), Flexible Spending Accounts (FSA), Basic Life/AD&D; Short-Term and Long-Term Disability, and an Employee Assistance Program (EAP). Other Voluntary Benefit Programs include a 401(k) plan, Wellness Incentive Program, Employee Stock Purchase Plan (ESPP), Supplemental Life/Critical Illness/Hospitalization/Accident Insurance, and Pet Insurance. Paid time off includes Company-observed U.S. Holidays, Floating Holidays, Vacation, Sick Time, a Volunteer Program, Paid Maternity and Paternity Leave, Bereavement Leave, Personal Leave and time off for voting.

How To Apply:

Incase you would like to apply to this job directly from the source, please click here

Responsibilities

The role involves designing, refining, and scaling prompt strategies for large language models to produce accurate, reliable, and high-value AI outputs by translating business needs into structured prompt frameworks. Responsibilities include systematic testing, building reusable prompt templates, implementing complex reasoning approaches like prompt chaining and RAG, and ensuring outputs meet quality and safety standards.