This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
We are seeking a Computer Vision Architect to lead the design and implementation of a real-time perception system that enables AI agents to understand and operate within complex game and simulated environments. This role will define how video, gameplay capture, and camera feeds are transformed into structured world representations that power intelligent NPC behavior and AI-driven systems within the Egofold ecosystem. You will work closely with engine, AI, and gameplay teams to architect scalable, production-ready vision pipelines integrated with Unreal Engine–based projects.
Job Responsibility:
Architect and implement real-time computer vision pipelines for analyzing gameplay video and camera feeds
Design systems that convert 2D visual input into structured 3D semantic world models usable by AI agents and NPC systems
Integrate perception modules into Unreal Engine–based runtimes and toolchains
Optimize inference performance for GPU-constrained, real-time environments
Define data collection, evaluation, and iteration strategies for improving perception robustness
Collaborate with AI engineers to design perception interfaces that feed behavior trees, agent systems, and decision models
Establish long-term technical direction for vision-driven gameplay and simulation features
Requirements:
5+ years of professional experience in computer vision, real-time perception, or related fields
Advanced degree (Master’s or PhD) in AI, Computer Vision, Robotics, or related field preferred
Proven experience building and deploying real-time video perception systems in production environments
Strong C++ proficiency and experience integrating systems into game engines or comparable real-time platforms
Deep understanding of object detection, tracking, temporal modeling, and 3D scene understanding
Experience optimizing models for deployment using CUDA, TensorRT, ONNX, or similar toolchains
Unreal Engine Experience: Proficiency with Unreal Engine, preferably UE4 or UE5
Nice to have:
Experience with multi-agent simulation, reinforcement learning environments, or game AI systems
Familiarity with graphics pipelines (deferred rendering, depth buffers, motion vectors, scene graphs)
Experience bridging synthetic and real-world datasets
Prior experience leading small technical teams or defining system architecture roadmaps
What we offer:
True focus on work/life balance
Paid company holidays, vacation, and separate sick leave