Location: Remote (Philippines)
Type: Full-Time
We are looking for a skilled AI Prompt Engineer with deep hands-on experience working with large language models (LLMs). You will be responsible for designing, testing, and optimizing prompts that drive accurate, consistent, and high-quality AI outputs across a range of business use cases. This is a fully remote role suited for someone who understands how LLMs think and knows how to get the best out of them.
Responsibilities
- Design, write, and refine prompts for LLMs including GPT-4, Claude, Gemini, and similar models
- Develop prompt libraries and reusable prompt templates for different business use cases
- Test and evaluate prompt performance, iterate based on output quality and consistency
- Fine-tune prompting strategies including chain-of-thought, few-shot, zero-shot, and role-based prompting
- Collaborate with automation, product, and content teams to embed prompts into workflows and tools
- Document prompt logic, versioning, and performance benchmarks
- Monitor LLM behavior and flag inconsistencies, hallucinations, or output drift
- Stay current with advances in LLM capabilities, new models, and prompting techniques
Requirements
- 1–2 years of hands-on experience working with LLMs in a professional setting
- Deep familiarity with at least two major LLMs (e.g., GPT-4, Claude, Gemini, Mistral)
- Strong understanding of prompt engineering techniques: chain-of-thought, few-shot, zero-shot, system prompts, and role prompting
- Experience with OpenAI API, Anthropic API, or similar
- Ability to evaluate and benchmark prompt outputs systematically
- Excellent written English — clarity and precision are critical in this role
- Strong analytical thinking and ability to work independently
NICE TO HAVE
- Experience with LangChain, LlamaIndex, or similar LLM frameworks
- Familiarity with fine-tuning or RLHF concepts
- Knowledge of AI automation tools (Make, Zapier, n8n)
- Experience building prompt-powered products or internal tools
