Prompt Engineer

About the Company:

Racine AI is a leading provider of SaaS solutions, enhancing the work of wealth management advisors through advanced AI capabilities. Operating across several countries, we deliver tools that automate administrative tasks, ensure regulatory compliance, and support personalized advisory services. Our AI is backed by up-to-date wealth management data and secure hosting in France. We are recognized for our innovative approach, high-quality service, and expertise in data-driven solutions.

Job Title: Prompt Engineer

Location: Remote / Hybrid / Office

Contract Type: Full-time / Freelance

Compensation: Based on experience

Job Description:

As a Prompt Engineer at Racine AI, you will develop and refine generative AI solutions that align with our business partners' objectives. Your role will involve designing prompt architectures and pipelines to enhance the capabilities of our models. This position provides exposure to a wide range of analytical tools and technologies, offering the chance to tackle complex challenges by integrating industry-leading practices.

Responsibilities:

• Collaborate with product and data teams to understand business needs and develop tailored AI solutions.
• Develop and optimize prompts to improve the accuracy and relevance of AI responses.
• Design and test models using advanced generative techniques (e.g., zero-shot/few-shot learning, fine-tuning).
• Integrate data sources via APIs and data pipelines to expand AI capabilities.
• Ensure high-quality code that adheres to security and web development standards.
• Effectively communicate results and recommendations to stakeholders.

Required Qualifications:

• Education: Master’s degree in Computer Science, Data Science, Computational Linguistics, or related technical field (advanced degree preferred).
• Experience: 4+ years in AI development, with expertise in generative text solutions and language models.
• Technical Skills:
• Proficiency in machine learning frameworks (e.g., TensorFlow, PyTorch) and production deployment of models.
• Experience in designing high-performance AI systems, including API development and data pipelines.
• Knowledge of NLP techniques such as entity extraction, encoder-decoder architectures, and semantic similarity.
• Strong Python coding skills for large-scale applications.
• Familiarity with cloud environments (e.g., Azure, AWS) for model deployment and management.
• Personal Attributes: Analytical mindset, team-oriented, excellent communication skills, and a passion for innovation.

Benefits:

• Work on large-scale AI projects with significant visibility.
• Flexible work environment (remote work options).
• Dynamic and collaborative team environment.
• Professional development and training opportunities in the latest AI advancements.

Start Date: ASAP