Principal Research Engineer, Unreal Assistant
About this role
Engineers who thrive at the intersection of game architecture and artificial intelligence will find a natural home developing intelligent tooling for Unreal Engine. The team focuses on integrating large language models directly into real-time development environments, creating agent-driven automation that helps creators build interactive experiences. Daily work involves designing full-stack systems that connect engine-side tooling with cloud infrastructure, allowing LLMs to operate natively inside the software. This role exists to push the boundaries of how developers interact with game technology by bridging deep engine internals with modern machine learning capabilities.
Candidates who excel here possess a strong systems background alongside practical experience with generative models and distributed services. The position requires someone capable of reasoning across C++ engine code, backend databases, and web interfaces to deliver reliable end-to-end features. Anyone joining the group will help define the technical direction for agent safety and evaluation while collaborating closely with multidisciplinary engineering peers.
What you will do
- Design and build LLM-driven agents and tools that operate directly inside Unreal Engine.
- Architect and extend the cloud-hosted agent harness, services, and database that mediate between language models and the engine.
- Work across the full stack to ship end-to-end features spanning engine tooling, cloud backends, and web user interfaces.
- Evaluate and integrate emerging LLM capabilities such as tool use and multi-agent orchestration into pipeline tooling.
- Define technical direction for the reliability, safety, and evaluation of LLM-driven engine automation.
- Partner closely with engine, tools, and backend engineers while mentoring others on game engine internals and machine learning system design.
What you need
- Demonstrate a strong software engineering background with hands-on experience in a game engine, with Unreal Engine strongly preferred.
- Bring practical experience building or shipping products powered by LLMs or a solid conceptual understanding of how language models operate.
- Possess experience with cloud-native services and infrastructure including web APIs, databases, and service architecture.
- Show excellent programming skills across C++ for engine-side work and Python or a web backend language.
- Maintain the ability to work full-stack and reason about tradeoffs across engine code, backend services, and web frontends.
- Display excellent written and verbal communication skills.
Benefits
- 100% of medical, dental, and vision HRA premiums covered for employees and dependents
- Long term disability, life insurance, and a 401k with competitive match
- Robust mental well-being program through Modern Health providing free therapy and coaching
- Unlimited PTO and sick time
- Company-wide paid breaks and a paid sabbatical for 7 years of employment
Skills and tech stack
Questions candidates ask
What kind of technology stack will I be working with?
You will work across the full stack utilizing C++ for engine-side tooling, Python or web backend languages, and cloud-native services to integrate LLMs directly into Unreal Engine.
What are the primary responsibilities for this role?
The role involves designing and building LLM-driven agents that operate inside Unreal Engine, architecting cloud-hosted agent harnesses, and evaluating emerging machine learning capabilities for engine automation.
What qualifications are required for applicants?
Applicants need a strong software engineering background with game engine experience, practical work with LLMs or a solid conceptual understanding of them, cloud infrastructure experience, and proficiency in C++ and Python.