Intern, Research - Context and Knowledge Systems for AI

Autodesk Research – Intelligent Construction

Summer 2027 | 12 weeks

Modern AI systems increasingly depend on their ability to access and use the right context at

the right time. An important research challenge is how large, evolving bodies of information

should be represented to support reliable inference.

Autodesk Research provides a distinctive setting for this work. Construction projects are rich,

complex information environments whose state changes continuously over time, making

them a compelling domain for studying context and knowledge systems for AI.

As a Research Intern, you will own a focused research problem in this area. You will

investigate new approaches to building and retrieving structured context, develop

experimental prototypes, and evaluate how effectively they support downstream AI

reasoning.

You will work closely with Autodesk researchers and engineers and have substantial freedom

to bring ideas from your own research. Strong contributions may form the basis of an

academic publication and future Autodesk research.

• Conduct original research in context and knowledge systems for AI. Investigate

methods for representing and retrieving information to support reliable contextual

inference

• Develop new approaches to context construction. Explore how relevant knowledge

can be identified and assembled dynamically from large and evolving information

environments

• Build research prototypes. Implement experimental systems using graph-based,

semantic or hybrid approaches and apply them to realistic project information

• Design and conduct rigorous experiments. Develop suitable research questions,

baselines and evaluation methods to understand the strengths and limitations of

proposed approaches

• Collaborate with Autodesk researchers and engineers. Work across AI research,

software engineering and domain expertise to refine ideas and translate them into

experimental systems

• Communicate research findings. Present results within Autodesk Research and

contribute, where appropriate, to research papers, technical reports and

demonstrations

• Currently enrolled in a PhD program in Computer Science, Artificial Intelligence,

Data Science, Information Science or a closely related field, with at least one

academic term remaining after the internship

• Research experience in an area related to knowledge representation, information

retrieval, data management or contextual information systems for AI

• Strong programming skills and experience developing experimental research

software

• Understanding of contemporary AI systems and how retrieval and contextual

information support modern reasoning or agentic workflows

• Experience formulating research questions and designing empirical evaluations.

• Strong written and verbal communication skills

Research experience in one or more of the following areas would be valuable:

• Knowledge graphs or graph-based information systems

• Advanced information retrieval and hybrid retrieval methods

• Retrieval-augmented generation, including GraphRAG or related approaches

• Context engineering or memory architectures for AI systems

• Semantic and structured knowledge representation

• Temporal, provenance-aware or evolving data systems

• Heterogeneous data integration at scale

• Graph machine learning applied to representation or retrieval

A strong research publication record in a relevant area is desirable

Prior experience with architecture, engineering or construction is not required. We are

particularly interested in candidates with deep technical expertise who are motivated by the

opportunity to test their research against a complex real-world information environment.

Autodesk Research explores technologies that may shape how the world is designed and

made. We work across fundamental and applied research, developing new ideas and testing

them against problems grounded in professional practice.

The Intelligent Construction team investigates how emerging forms of AI can support a more

connected and adaptive construction industry. An important part of that challenge is

understanding how fragmented project information can become a coherent and evolving

source of knowledge for intelligent systems.

You will join a multidisciplinary research environment with expertise spanning AI, data

systems, software engineering and construction. You will work closely with experienced

researchers while having substantial ownership of your own research problem.

Expected Research Outcome

This is a focused 12-week research internship. The research question will be developed with

the successful candidate to make use of their existing expertise while addressing a problem

relevant to the team's research direction.

By the end of the internship, we expect the intern to have developed and evaluated an original

approach to a clearly defined research problem. This should include a working research

prototype, rigorous experimental evidence and a clear account of the findings and limitations.

The work will be shared within Autodesk Research. Where the research contribution warrants

it, we would expect to develop the work toward publication at an appropriate academic

venue.

Welcome to Autodesk! Amazing things are created every day with our software – from the greenest buildings and cleanest cars to the smartest factories and biggest hit movies. We help innovators turn their ideas into reality, transforming not only how things are made, but what can be made.

We take great pride in our culture here at Autodesk – it’s at the core of everything we do. Our culture guides the way we work and treat each other, informs how we connect with customers and partners, and defines how we show up in the world.

When you’re an Autodesker, you can do meaningful work that helps build a better world designed and made for all. Ready to shape the world and your future? Join us!

Salary is one part of Autodesk’s competitive compensation package. Offers are based on the candidate’s experience, educational level, and geographic location.

This role may require in-person onboarding and/or in-person ID verification.