Job Description
We are seeking a visionary Senior Prompt Engineer to lead our AI initiatives in Chicago. As a pioneer in the generative AI space, we are looking for a technical expert who can bridge the gap between human intent and machine logic. If you are passionate about Large Language Models (LLMs) and want to shape the future of human-computer interaction, this is your chance to make a significant impact.
Why This Role is Unique:
- Attractive Sign-On Bonus: We are offering a $5,000 sign-on bonus to top-tier talent joining our team immediately.
- Work on cutting-edge AI products used by Fortune 500 clients.
- Hybrid work model allowing for collaboration in our modern Chicago office.
In this role, you will be responsible for optimizing the performance of our AI models and ensuring they deliver accurate, safe, and creative outputs. You will work alongside data scientists and software engineers to integrate prompt strategies into scalable production systems.
Responsibilities
- Design, test, and refine complex prompts to maximize the accuracy and relevance of LLM outputs.
- Develop and implement prompt engineering best practices, frameworks, and libraries.
- Conduct rigorous A/B testing to compare prompt variations and analyze results.
- Collaborate with the product team to translate business requirements into effective AI solutions.
- Maintain a deep understanding of the latest research in NLP, Transformer architectures, and AI safety.
- Train and fine-tune models using prompt-based learning techniques.
Qualifications
- Bachelor’s degree in Computer Science, Linguistics, or a related technical field (Master’s preferred).
- 3+ years of experience in Natural Language Processing (NLP) or AI engineering.
- Strong proficiency in Python and experience with libraries such as Hugging Face, LangChain, or OpenAI API.
- Deep understanding of LLM architectures (e.g., GPT-4, BERT, Llama) and how to leverage them.
- Exceptional written communication skills and creative problem-solving abilities.
- Experience with data analysis and statistical methods for evaluating model performance.