Research Engineer — 3D Reconstruction and Rendering
San Francisco
Full Time Senior-level / Expert USD 175K - 280K
Sesame
Book same-day care with board-certified providers, specialists, labs & more - at half the price. No waiting rooms. No surprise bills. No insurance needed.About Sesame
Sesame believes in a future where computers are lifelike - with the ability to see, hear, and collaborate with us in ways that feel natural and human. With this vision, we're designing a new kind of computer, focused on making voice companions part of our daily lives. Our team brings together founders from Oculus and Ubiquity6, alongside proven leaders from Meta, Google, and Apple, with deep expertise spanning hardware and software. Join us in shaping a future where computers truly come alive.
About the Role
Vision understanding is a critical addition to conversational AI, bridging the gap between speech and the physical world. We‘re looking for a skilled engineer or researcher to build photorealistic digital twins of the facial region, serving as a foundational layer in our vision development infrastructure. The ideal candidate will be fluent in classical techniques—such as multiview geometry, photogrammetry, and reflectance modeling—while also comfortable leveraging modern machine learning tools, from fine-tuning neural rendering models to integrating off-the-shelf pipelines. You’ll collaborate with research, hardware, and product teams to build high-fidelity capture and rendering systems that combine physical accuracy with visual realism.
Responsibilities:
Collaborate with hardware and optics teams to design and operate facial capture systems (e.g., light stages, multi-camera rigs).
Develop offline reconstruction pipelines using captured data that produce subject-specific digital twins with high geometric and photometric fidelity.
Implement algorithms to render individuals under novel viewpoints, lighting conditions, and facial configurations using dense multiview data.
Build end-to-end systems—from capture and calibration to data curation, rendering evaluations, and deployment.
Evaluate existing techniques from graphics, vision, and ML literature; prototype and adapt them to meet our unique objectives.
Where needed, invent new approaches that push the boundaries of facial reconstruction and appearance modeling.
Required Qualifications:
Demonstrated experience with 3D reconstruction, photorealistic rendering, or appearance modeling from captured data.
Strong understanding of multiview geometry, camera calibration, and physical light transport.
Ability to navigate and deliver results in high-ambiguity, open-ended problem spaces.
Familiarity with large-scale dataset handling, including multi-camera datasets.
Excellent communication skills and the ability to work collaboratively across disciplines.
Bachelor’s degree or higher in computer graphics, vision, imaging, machine learning, or a related field.
Preferred Qualifications:
Master’s or Ph.D. in a relevant discipline.
Hands-on experience training or adapting neural rendering models (e.g., NeRF, relighting networks, inverse rendering).
Proficiency in PyTorch, JAX, or other modern ML frameworks.
Sesame is committed to a workplace where everyone feels valued, respected, and empowered. We welcome all qualified applicants, embracing diversity in race, gender, identity, orientation, ability, and more. We provide reasonable accommodations for applicants with disabilities—contact careers@sesame.com for assistance.
Full-time Employee Benefits:
401k matching
100% employer-paid health, vision, and dental benefits
Unlimited PTO and sick time
Flexible spending account matching (medical FSA)
Benefits do not apply to contingent/contract workers
Tags: 3D Reconstruction Conversational AI JAX Machine Learning NeRFs Pipelines PyTorch Research
Perks/benefits: Career development Flexible spending account Flex vacation Health care Unlimited paid time off
More jobs like this
Explore more career opportunities
Find even more open roles below ordered by popularity of job title or skills/products/technologies used.