Mid Prompt Engineering Specialist

This is a fully remote position, open to applicants in Greece.

📋 Description

• Create, test, and continuously improve prompts for applications based on large language models (LLMs).

• Establish and manage libraries of prompts, templates, and reusable prompt elements.

• Assess and compare prompt effectiveness across various LLM platforms and model iterations.

• Convert functional and business requirements into successful prompt strategies.

• Utilize techniques such as zero-shot, few-shot, retrieval-augmented generation (RAG), role prompting, and structured output prompting.

• Detect and address hallucinations, prompt injection, data leakage, bias, and inconsistencies in outputs.

• Outline and document decisions related to prompt design, evaluation standards, and version history.

• Assist in testing, quality assurance, and user acceptance testing activities for LLM solutions.

• Create automation and testing pipelines for evaluating prompts.

• Integrate prompts and LLM functionalities via APIs.

• Offer guidance and knowledge transfer to both technical and non-technical stakeholders regarding effective interaction patterns with LLMs.

⛳️ Requirements

• At least 2 years of professional experience in working with and optimizing LLMs and/or prompt development and engineering.

• A Bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, IT, or a related field; alternatively, a non-university degree combined with a minimum of 5 years of IT experience.

• Practical experience with major LLM platforms and APIs, including OpenAI/GPT, Anthropic/Claude, Mistral, Meta LLaMA, or similar commercial or open-source models.

• In-depth understanding of prompt design methods, such as zero-shot, few-shot, RAG, role prompting, and structured output prompting.

• Experience with frameworks for orchestrating LLMs.

• Programming abilities for automating prompts, creating testing pipelines, and integrating APIs.

• Familiarity with methodologies for assessing LLM outputs, incorporating both human evaluation and automated metrics.

• Knowledge of LLM architecture and tokenization sufficient to inform effective prompt design choices.

• Awareness of common risks associated with LLMs, including hallucinations, prompt injection, data leakage, and bias.

• Strong understanding of how various LLMs react to prompt design and context.

• Capability to experiment, assess, and methodically enhance AI outputs.

• Skill in transforming business needs into structured and reusable prompt strategies.

• Commitment to quality in LLM testing and evaluation.

• Comprehension of both technical and business dimensions of Generative AI solutions.

• Proficient in effectively communicating AI concepts to both technical and non-technical audiences.

🏝️ Benefits

• Engage in cutting-edge Generative AI and LLM-based projects.

• Acquire practical experience with a variety of commercial and open-source LLM platforms.

• Work with contemporary techniques in prompt engineering, RAG, orchestration, and evaluation.

• Collaborate with seasoned professionals in AI, technology, and business.

• Continue enhancing your skills in LLM engineering and enterprise-level Generative AI.