About the role#
We are looking for interns to join a pod building an enterprise AI capability. This tool helps leadership move from information to insight by retrieving from document collections, querying structured data, and calling live data sources. You will focus on agent design, retrieval, grounding, citation, evaluation, and guardrails to help move the project toward production.
What you'll need#
- Currently enrolled in a Bachelor's, Master's, or PhD program in Computer Science, AI/Machine Learning, Data Science, Software Engineering, or a related field.
- Strong Python skills and hands-on experience with LLM APIs or frameworks.
- Practical understanding of RAG, embeddings, vector search, and LLM evaluation methods.
- Awareness of LLM reliability and security risks, including hallucination, prompt injection, and data leakage.
- Familiarity with software engineering practices including Git, testing, APIs, and basic CI/CD.
- Experience with multi-agent or tool-calling architectures, or with Azure AI Search, Microsoft Foundry, or Copilot Studio agents.
- Coursework or interest in AI governance, Responsible AI, model risk, or technology law.
- Experience with financial, market, or legal documents is a plus.
- Ability to bridge the gap between business and technology teams by explaining technical work in business terms.
- Excellent verbal presentation skills and experience presenting to senior leaders.
What you'll do#
- Translate business processes, decision rules, and stakeholder handoffs into agent steps, tools, and approval points within a multi-agent workflow.
- Design and prototype agent orchestration, tool use, and prompts on enterprise AI platforms.
- Experiment with chunking, embeddings, hybrid search, re-ranking, and metadata filtering.
- Build question sets from real executive inquiries to measure accuracy, groundedness, citation fidelity, and hallucination rates.
- Ensure every answer cites its source and indicates how current the information is.
- Track answer quality, latency, and consumption over time to recommend tuning.
- Prepare inputs for architecture reviews, Responsible AI and model risk validation, and audit readiness.
- Provide regular progress updates to senior leadership, adjusting the level of detail for executive and technical audiences.
- Turn governance and risk requirements into design patterns like human approval points and access boundaries.
- Write technical documentation and decision records.
- Partner with data and cybersecurity interns on secure connectors and test plans.
Location & details#
- Term: Winter 2027 (January to June 2027).
- Commitment: At least 30 hours per week.
- Modality: Hybrid, with onsite work required 4 days per week.
- Locations: Burlington, MA and Quincy, MA.
- Employment: Full-time internship.
- Compensation: Paid internship.


