Data Scientist

Bilingual Data Scientist On-site in Greenwood Village, CO $40-$50/hour 1-year long W2 contract with benefits About the Role Our client is seeking a bilingual (English + Spanish) Data Scientist to take ownership of an in‑progress Large Language Model (LLM) project. The core solution is already built using GPT-based models, and the team has implemented recursive results and foundational architecture. Your role will be to continue model development, refine existing pipelines, improve performance, and support delivery ahead of the February deadline. You will work closely with cross-functional IT and data teams, transforming complex data into actionable insights while adhering to strict privacy, compliance, and organizational standards. This position is ideal for someone who thrives in fast-paced, research-driven environments and is comfortable working with modern AI tools and cloud technologies. Key Responsibilities • Develop, refine, and productionize LLM‑based models, including a partially built GPT-driven solution. • Apply data science and machine learning techniques such as clustering, regression, decision trees, SVMs, k‑nearest neighbors, collaborative filtering, matrix factorization, and market basket analysis. • Conduct prompt engineering and retrieval‑augmented generation (RAG) workflows for model optimization. • Improve model accuracy, relevance, and stability using advanced data mining and NLP techniques. • Process and translate complex research data into clear, actionable insights. • Work collaboratively with IT teams to design and maintain models within technology and privacy guidelines. • Ensure strict adherence to data privacy and industry compliance standards. • Utilize Azure-based tools, including Azure Databricks, for model training, deployment, and scalability. • Communicate findings clearly in both English and Spanish, supporting bilingual model development and evaluation. • Build internal and external professional networks to validate ideas and collaborate on complex challenges. Required Qualifications • 1–5 years of professional experience as a Data Scientist or in a similar analytical role. • Bilingual fluency in English and Spanish (written and verbal). • Practical experience working on AI or LLM-related projects (GPT or similar models). • Hands-on experience with: • Prompt engineering • Retrieval-Augmented Generation (RAG) • GPT-based or other LLM architectures • NLP techniques (SpaCy experience is a plus) • Strong analytical skills with proven experience using clustering, regression analysis, decision trees, SVMs, etc. • Proficiency with Azure cloud services, especially Azure Databricks. • Strong communication skills with the ability to translate technical content for non-technical audiences. • Demonstrated experience working with strict data privacy and data governance standards. Preferred Skills • Experience with recursive model workflows. • Familiarity with SpaCy-based NLP solutions. • Exposure to industrial-grade computing environments or proprietary research tools. • Strong teamwork and collaboration abilities. Why This Role Matters The LLM solution is already underway, and the core architecture is in place. This role is crucial for ensuring final delivery—your contributions will directly influence model performance, bilingual capability, and the success of the product launch in February.