Data Scientist with expertise in Prompt Engineering and Generative AI

Halo believes in innovation by inclusion to solve digital problems. As an international agency of over 200 people specializing in interactive media strategy and development, we embrace equity and empowerment in a serious way. Our interdisciplinary teams of unique designers, developers and entrepreneurial minds with a variety of backgrounds, viewpoints, and skills connect to solve business challenges of every shape and size. We empathize to form deep, meaningful relationships with our clients so they can do the same with their audience. Working at Halo feels like belonging. Learn more about our philosophy, benefits, and team at https://halopowered.com/

About the Role

We are seeking a highly skilled Data Scientist with expertise in Prompt Engineering and Generative AI to join our advanced AI initiatives team on a temporary assignment. You will play a critical role in developing and optimizing Retrieval-Augmented Generation (RAG) systems, refining LLM prompts, and deploying AI-driven applications that extract value from structured and unstructured data. This role is ideal for someone who thrives in a hands-on, experimental environment and enjoys pushing the boundaries of large language model capabilities.

Key Responsibilities

• Design, develop, and optimize prompts to enhance the relevance, accuracy, and usefulness of AI-generated outputs.
• Build and maintain RAG pipelines using Atlas Vector Search, relational databases, and proprietary datasets.
• Develop, train, and evaluate machine learning models, focusing on retrieval-based and agentic architectures.
• Conduct A/B tests and structured experiments to validate prompt effectiveness.
• Analyze user interactions and system performance to identify improvement opportunities.
• Collaborate cross-functionally with product, engineering, and content teams to align AI output with business objectives.
• Create reproducible ML workflows using Docker and support scalable deployments.
• Design insightful dashboards and reports to communicate AI model impact and performance.

Must-Have Qualifications

• Proven experience with Prompt Engineering, including fine-tuning or prompt tuning strategies for LLMs (ideally 4.o models).
• Hands-on experience with RAG systems and semantic retrieval using Atlas Vector Search.
• Proficiency in Python for data processing, ML modeling, and scripting.
• Strong knowledge of Relational Databases (PostgreSQL, MySQL) for data integration.
• Experience with Docker for containerization and workflow reproducibility.
• Ability to design and interpret experiments using data-driven decision making.
• Excellent communication skills with a talent for simplifying complex AI topics.

Nice-to-Have Skills

• Experience with Agentic AI systems and multi-step reasoning architectures.
• Familiarity with Apache Kafka for event streaming and real-time pipelines.
• Knowledge of Kubernetes (K8s) for orchestrating ML workloads.
• Experience with Node.js for backend/API integration.
• Familiarity with UX principles and/or BI tools like Streamlit, Dash, Power BI, or Tableau.

Benefits

• 100% Remote Work.
• Salary in USD!
• Get to work on challenging projects for the U.S!