INTERNSHIP: Generative AI Engineering
Job details
Our Dassault Systemes Generative AI Portfolio Team is excited to announce we have a full-time internship opportunity available in our San Diego, CA or Durham, NC office!
Team overview
The BIOVIA Generative AI Portfolio team shapes how scientific workflow software evolves in the era of AI agents, Generative AI, and machine learning. We work closely with Engineering, UX, and Product to translate emerging AI capabilities into practical, reliable, and scalable experiences for scientific users.
Role summary
We are looking for a technically strong intern to help prototype and evaluate a generative visual scripting system for scientific workflows. In this role, you will build and test AI agents that can create and modify workflow pipelines through structured tool use.
This is a hands-on applied AI engineering internship focused on prototyping, orchestration logic, tool integration, validation, and evaluation. It is best suited for candidates who enjoy building working systems, experimenting quickly, and learning from real technical constraints.
1-Technical experimentation & prototyping:
Prototype an agent that creates and modifies visual workflows by invoking MCP tools.
Implement orchestration logic: tool selection, parameter completion, step-by-step execution, retries, and safe fallbacks.
Build utilities for schema inspection, validation, and automated correctness checks.
2-Tooling integration (MCP):
Build and iterate on tools and tool schemas (inputs/outputs, constraints, error handling) to ensure predictable agent behavior.
Add guardrails: allowlists, parameter bounds, compatibility checks.
3-Evaluation & quality framework
Define a benchmark set of visual scripting tasks (create from intent, edit, refactor, debug).
Build an evaluation harness to measure correctness, robustness, and repeatability.
4-Expected outcomes
A working prototype demonstrating tool-based generative visual scripting in a controlled environment.
A repeatable evaluation suite with benchmark scenarios and metrics.
A short report summarizing results, key failure modes, and recommendations for next iterations.
A repeatable evaluation suite with benchmark scenarios and metrics.
A short report summarizing results, key failure modes, and recommendations for next iterations.
Master’s (or equivalent experience) in Computer Science, Engineering, Data Science, AI/ML.
Strong Python skills (APIs, data structures, debugging, packaging).
Familiarity with LLMs and agent/tool patterns (function calling, tool routing, structured outputs).
Comfort working with JSON schemas, validation, and integration-style development.
Clear written communication for documenting experiments and results.
Nice to have:
Experience with workflow/pipeline tools and visual editors (Pipeline Pilot, KNIME, Alteryx, Dataiku).
Experience with REST APIs, async execution, and software testing (unit/integration).
Exposure to RAG, prompt engineering, ReAct or LLM evaluation methods.
Experience with the MCP framework.
In addition to working with your direct team, as a member of Dassault Systemes NAM Intern Program you will be invited to our Speaker Series, Lunch and Learns, Networking Events and employee functions.
Besides the above, a sense of adventure and a willingness to have fun through work are great tools at our disposal. If you enjoy learning new things while working with a friendly group of highly skilled individuals, this could be a great fit for you! We look forward to meeting with you and learning why you feel you would make a great Dassault Systemes Intern.
Shape your career with 3DS! #WeAre3DS
