Data Scientist Intern- Digital Engineering
About The Position
We are excited to offer an internship opportunity for a Data Scientist Intern to support applied research and implementation of LLM-based, agentic AI frameworks and MCP server architectures for intelligent data filtering, querying, and reporting. The role focuses on designing and prototyping AI agents capable of autonomously orchestrating data access, analysis, and reporting using natural language interfaces. At SMS group, our people are our greatest asset. We offer an entrepreneurial environment that promotes a culture of innovation, growth, and inclusion. We offer company events, activities, and opportunities to participate in charitable initiatives that benefit the communities where we are located.
Requirements
- Ongoing studies in Data Science, Computer Science, AI, or a related technical field.
- Strong interest in Large Language Models, agentic AI frameworks, and applied NLP.
- Practical experience with Python and modern AI/ML libraries; familiarity with LLM APIs, embeddings, retrieval-augmented generation (RAG), or tool orchestration is an advantage.
- Basic understanding of data engineering concepts (SQL, APIs, data pipelines).
- Ability to work independently on research questions and communicate results clearly to technical and non-technical stakeholders.
Responsibilities
- Research and prototype LLM-based solutions for querying, filtering, and summarizing industrial data used in reporting applications.
- Design and implement agentic AI workflows where LLM-based agents autonomously plan, execute, and validate data access and reporting tasks.
- Support the development and integration of MCP server architectures enabling secure, structured, and performant interaction between LLMs and enterprise data sources.
- Develop natural-language interfaces for accessing time-series and relational data, including prompt design, tool calling, and context management.
- Collaborate closely with domain experts, software and reporting teams to translate industrial use cases into LLM-driven data solutions.
- Implement prototypes in Python, integrate them into backend services, and evaluate performance, robustness, and response quality.
- Analyze feedback and usage data to iteratively improve prompts, agent behavior, retrieval strategies, and data representations.
Benefits
- Competitive compensation
- medical/dental/vision coverage
- paid vacation
- paid holiday time
- 401k with a company match
- training
- a tuition reimbursement program
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Career Level
Intern
Education Level
No Education Listed
