Data Scientist, Prompt Engineering & LLMs

Eliassen Group; Englewood (CO); Hybrid; Confidential; Full time

Benefits offered by this job

Medical, Dental, Vision benefits

401k with company matching

Life insurance

Job summary

Eliassen Group is seeking a data scientist focused on prompt engineering, LLMs, and A/B testing in Colorado. You will design, develop, and optimize prompts for AI applications and integrate LLM capabilities into existing workflows.

Responsibilities include designing RAG-based solutions, conducting experiments, and performing rigorous statistical analyses to improve model performance while ensuring data privacy and security.

Qualifications

• Hands-on experience with prompt engineering and RAG patterns.
• Expertise in A/B testing and experimentation for LLMs.
• Proficiency in Python and SQL for data processing and model workflows.
• Familiarity with AWS services supporting AI/ML workloads.
• Experience applying AI/ML methodologies to production use cases.
• Advanced analytical, problem-solving, and research skills.
• Strong oral and written communication abilities.

Responsibilities

• Configure and integrate LLM solutions into existing systems and workflows to deliver high-quality outputs.
• Design and optimize prompts for RAG-based and LLM-powered applications.
• Plan and execute A/B tests and experimentation frameworks for LLM features and outputs.
• Conduct rigorous statistical analyses to validate findings and improve model performance.
• Analyze and preprocess large datasets to train and fine-tune language models.
• Create comprehensive documentation and provide training on best practices.
• Ensure data privacy and security compliance in all AI activities.
• Contribute to innovative AI products that add measurable business value.

Skills

Prompt engineering

RAG patterns

AB testing

Python

SQL

AWS

AI/ML production

Data analysis

Communication

Job description

Description

Hybrid 4 onsite / 1 work from home in Greenwood Village, CO

Our client seeks data scientists focused on prompt engineering, large language models, and A/B testing. You will design, develop, and optimize prompts for AI applications with emphasis on retrieval-augmented generation and LLM integration. You will partner with cross-functional teams to embed LLM capabilities into existing workflows, drive experimentation and statistical evaluation, and contribute to a growing portfolio of GenAI initiatives supporting customer experience and internal operations.

Due to client requirements, applicants must be willing and able to work on a w2 basis. For our w2 consultants, we offer a great benefits package that includes Medical, Dental, and Vision benefits, 401k with company matching, and life insurance.

Rate: $58.00 to $62.00/hr. w2

JN -092026-108578

Responsibilities

• Configure and integrate LLM solutions into existing systems and workflows to deliver high-quality, relevant outputs.
• Design and optimize prompts for RAG-based and LLM-powered applications.
• Plan and execute A/B tests and experimentation frameworks for LLM features and outputs.
• Conduct rigorous statistical analyses to validate findings and improve model performance.
• Analyze and preprocess large datasets to train and fine-tune language models.
• Create comprehensive documentation and provide training on best practices.
• Ensure data privacy and security compliance in all AI activities.
• Contribute to innovative AI products that add measurable business value.

Experience Requirements

• Hands-on experience with prompt engineering and RAG patterns.
• Expertise in A/B testing and experimentation for LLMs.
• Proficiency in Python and SQL for data processing and model workflows.
• Familiarity with AWS services supporting AI/ML workloads.
• Experience applying AI/ML methodologies to production use cases.
• Advanced analytical, problem-solving, and research skills.
• Strong oral and written communication abilities.