Mid Prompt Engineering Specialist

We are looking for aPrompt Engineering Specialist to design, optimize, evaluate, and maintain prompts forLarge Language Model (LLM) applications.

In this role, you will work with modern LLM platforms and orchestration frameworks, collaborating with Business Analysts, domain experts, and technical teams to translate functional requirements into effective and reliable prompt strategies.

Key Responsibilities

• Design, test, and iteratively refine prompts forLLM-based applications
• Develop and maintainprompt libraries, templates, and reusable prompt components
• Evaluate and benchmark prompt performance across different LLM platforms and model versions
• Translate functional and business requirements into effective prompt strategies
• Apply advanced prompt-engineering techniques, includingzero-shot, few-shot, RAG, role prompting, and structured output prompting
• Identify and mitigate risks such ashallucinations, prompt injection, data leakage, bias, and inconsistent outputs
• Define and document prompt design decisions, evaluation criteria, and version history
• Support testing, Quality Assurance, and User Acceptance Testing activities for LLM solutions
• Develop automation and testing pipelines for prompt evaluation
• Integrate prompts and LLM capabilities through APIs
• Provide guidance and knowledge transfer to technical and non-technical stakeholders on effective LLM interaction patterns

• Minimum 2 years of professional experience working with and optimizing LLMs and/or prompt development and engineering
• Bachelor’s degree inComputer Science, Artificial Intelligence, Data Science, IT, or a closely related field; alternatively, a non-university degree with at least5 years of IT experience
• Hands-on experience with majorLLM platforms and APIs, such as:
• • OpenAI / GPT
  • Anthropic / Claude
  • Mistral
  • Meta LLaMA
  • Equivalent commercial or open-source models
• Strong knowledge of prompt design techniques, includingzero-shot, few-shot, RAG, role prompting, and structured output prompting
• Experience withLLM orchestration frameworks
• Programming skills for prompt automation, testing pipelines, and API integration
• Experience with methodologies for evaluating LLM outputs, including human evaluation and automated metrics
• Understanding ofLLM architecture and tokenization sufficient to support effective prompt-design decisions
• Understanding of common LLM risks, including hallucination, prompt injection, data leakage, and bias

You will be a great candidate for us if you

• Have a strong understanding of how different LLMs respond to prompt design and context
• Enjoy experimenting, evaluating, and systematically improving AI outputs
• Can translate business requirements into structured and reusable prompt strategies
• Have a quality-focused approach to LLM testing and evaluation
• Understand both the technical and business aspects of Generative AI solutions
• Can communicate AI concepts effectively to technical and non-technical stakeholders

Why join inventYOU

• Work on innovativeGenerative AI and LLM-based solutions
• Gain hands-on exposure to multiple commercial and open-source LLM platforms
• Work with modern prompt engineering, RAG, orchestration, and evaluation techniques
• Collaborate with experienced AI, technology, and business professionals
• Continue developing your expertise inLLM engineering and enterprise Generative AI