New 
Research Intern - Neural Rendering & Character AI (Applied Science)
 Microsoft | |
 United States, Washington, Redmond | |
 Oct 24, 2025 | |
|
OverviewResearch Internships at Microsoft provide a dynamic environment for research careers with a network of world-class research labs led by globally-recognized scientists and engineers, who pursue innovation in a range of scientific and technical disciplines to help solve complex challenges in diverse fields, including computing, healthcare, economics, and the environment.Join the Applied Sciences group in the Windows organization to push the frontier of neural rendering and generative 3D/4D for digital humans and interactive characters. We explore image-to-3D, Gaussian splatting, neural/implicit scene representations, diffusion-based 3D and 4D generation, speech-/text-driven facial animation, and controllable character behaviors. Projects span high-fidelity offline research to efficiency-minded prototypes, with an emphasis on scientific rigor, reproducibility, and user-centric evaluation.
ResponsibilitiesResearch Interns put inquiry and theory into practice. Alongside fellow doctoral candidates and some of the world's best researchers, Research Interns learn, collaborate, and network for life. Research Interns not only advance their own careers, but they also contribute to exciting research and development strides. During the 12-week internship, Research Interns are paired with mentors and expected to collaborate with other Research Interns and researchers, present findings, and contribute to the vibrant life of the community. Research internships are available in all areas of research, and are offered year-round, though they typically begin in the summer. Additional ResponsibilitiesConduct original research and build prototypes in areas such as:Neural rendering & scene representations (radiance fields, Gaussian splats, hybrid implicit/explicit models, dynamic/deformable fields).Generative 3D/4D (image-/video-/text-conditioned 3D generation, diffusion/score-based methods, consistency & editability).Digital human & facial animation (speech-/audio-driven animation, identity/expression control, temporal coherence).Interactive character intelligence (learned controllers, multimodal conditioning, behavior/style control).Design datasets and evaluation protocols; perform ablations and benchmark against public and internally curated evaluations.Optimize for fidelity, robustness, or efficiency depending on project goals (e.g., high-quality offline pipelines or compact interactive models).Communicate results via talks, internal tech reports, and-when appropriate-submissions to top venues. | |