Prompt Engineer

Job Title: Prompt Engineer

Location: Krakow, Poland – 3 days onsite in a week (It’s a Must, no negotiations)

Duration: 6+ Months Contract

Rate: 1565 PLN/day on B2B Contract

Experience: 10-12 Years

About the Role:

We are seeking a skilled Prompt Engineer to join our AI/ML team and lead the development of high-quality prompts for large language model (LLM) applications. You will play a key role in designing, testing, and optimizing prompts for real-world use cases, ensuring accuracy, consistency, and safety in LLM outputs.

Key Responsibilities:

• Design, test, and deploy prompts for LLMs across multiple production-grade projects.

• Collaborate with product and engineering teams to translate business requirements into effective prompt logic.

• Implement and optimize prompt engineering frameworks using Python and LLM APIs.

• Evaluate prompt performance using metrics like BLEU, ROUGE, and semantic similarity.

• Integrate human-in-the-loop validation processes to ensure prompt quality and relevance.

• Contribute to fine-tuning and Retrieval-Augmented Generation (RAG) pipelines.

• Address LLM security concerns including prompt injection, output filtering, and API limitations.

• Structure outputs for downstream consumption in applications and workflows.

Required Skills & Qualifications:

• Proven experience with 2+ LLM production projects involving prompt design and deployment.

• Strong understanding of prompt structure, context management, and output formatting.

• Proficiency in Python, including libraries like Pandas, and experience with LLM APIs.

• Hands-on experience with fine-tuning or RAG pipelines.

• Familiarity with prompt evaluation tools and metrics.

• Knowledge of LLM security best practices.

• Excellent communication skills and ability to work cross-functionally.

• Analytical mindset with attention to both high-level design and low-level output consistency.

Good to Have:

• Experience with vector databases and retrieval-augmented generation.

• Exposure to tools like LangChain, LlamaIndex, or similar frameworks.

• Prior work with OCR, NLP, or Intelligent Document Processing (IDP) pipelines.