About MutualArt:
MutualArt is a global leader in providing comprehensive data and insights for the art market. For nearly two decades, we've been at the forefront of leveraging technology to make the art world more accessible and transparent for collectors, enthusiasts, artists, and art professionals worldwide. Our extensive database encompasses millions of auction results, artist records, exhibition listings, and market analyses, making us a go-to resource for understanding the intricate dynamics of the global art ecosystem.
About the Role:
We are seeking a highly skilled Prompt Engineer with strong expertise in Python and hands-on experience working with Large Language Models (LLMs). You will be responsible for designing, testing, and optimizing prompts to improve the performance, accuracy, and consistency of AI-driven solutions. This role bridges software engineering and applied AI, requiring both technical rigor and creativity.
Key Responsibilities:
- Design, develop, and optimize prompts for LLMs to ensure accurate, consistent, and reliable outputs
- Implement prompt engineering techniques such as few-shot learning, chain-of-thought, and structured output generation
- Work with LLM APIs (OpenAI, Gemini, Hugging Face, etc.) to integrate AI capabilities into production workflows
- Develop and maintain Python scripts, APIs, and automation pipelines to support prompt experiments and deployment
- Define and validate JSON schemas for structured outputs, ensuring compatibility with downstream systems
- Collaborate with product, data, and engineering teams to align prompt design with business requirements
- Benchmark, monitor, and continuously improve model responses and system performance
Required Qualifications:
- Strong proficiency in Python programming (data structures, APIs, debugging)
- Hands-on experience with LLM APIs such as OpenAI, Gemini, Hugging Face, or similar
- Proven knowledge of prompt engineering techniques (few-shot, role-based prompting, structured output parsing)
- Understanding of JSON schemas and structured output validation
- Experience with Flask, FastAPI, or similar frameworks for building and integrating APIs
- Ability to optimize prompts for scalability, reliability, and performance in production environments
- Strong problem-solving skills and ability to work in a fast-paced, iterative development environment
Preferred Skills (Nice To Have)
- Familiarity with vector databases (e.g., Pinecone, Qdrant, OpenSearch)
- Knowledge of evaluation frameworks for LLMs
- Experience with cloud platforms (AWS, GCP, Azure) for AI deployments
- Background in NLP, applied ML, or AI research
What We Offer:
- Competitive compensation package
- Opportunity to work on cutting-edge AI applications
- Flexible work arrangements (remote/hybrid)
- Collaborative, innovative, and growth-focused environment
