Join Mecka AI as a Research Scientist to architect and train 3D reconstruction pipelines for robotics and embodied AI.
Posted by employer 1 week ago
First seen on Joblaze 3 hours ago
Last verified on the company career page 3 hours ago
Skills & Technologies
What you'll build
- Design, train, and scale models for dense 3D geometry extraction
- Reconstruct high-fidelity digital twins of real-world environments
- Compress and optimize 3D scene representations for client delivery
- Rapidly prototype new architectures for dynamic actor isolation
- Integrate reconstructed environments to improve perception pipeline
Must have
- Deep expertise in 3D Computer Vision
- Proven experience training large-scale 3D vision models
- Experience writing custom CUDA kernels
Nice to have
- First-author publications in top-tier venues
- Projects deploying 3D assets to WebGL
- Experience with custom rendering engines
AI in the day-to-day
Mecka uses artificial intelligence (AI) responsibly to support administrative and efficiency-focused aspects of our recruitment process.
Requirements
- Education
- PhD
Not disclosed in this posting: compensation, years of experience, work arrangement, visa sponsorship.
Joblaze summary
In this role, the Research Scientist focuses on developing and training advanced 3D reconstruction pipelines to create photorealistic digital environments from real-world data. Key skills include expertise in 3D computer vision, neural rendering, and experience with large-scale models using PyTorch. This position is ideal for candidates with a strong background in deep learning and spatial modeling, particularly those with a track record of impactful research. Mecka AI offers access to extensive proprietary data, enhancing the potential for significant contributions to embodied AI systems.
Joblaze insights
- Listed today — first seen on Joblaze October 12, 2026. Last confirmed on Mecka AI's careers page October 12, 2026.
Quick facts
- What's the tech stack?
- Joblaze extracted these technologies from the posting: 3D Computer Vision, CUDA, Multi-view Geometry, PyTorch, neural rendering, spatial modeling.
- What seniority level is this role?
- Mecka AI targets senior candidates for this position.
- Is this full-time or contract?
- Full-time for this Research Scientist – 3D Environment Reconstruction role at Mecka AI.
From the original posting
The Role
We are hiring a Research Scientist to architect and train proprietary 3D reconstruction pipelines from scratch.
You will transform our continuous stream of high-quality, real-world multi-modal data into highly accurate, photorealistic digital environments using techniques such as 3D Gaussian Splatting and NeRFs. Beyond building the core architectures, you will integrate these reconstructed environments to improve other segments of our perception pipeline and optimize these spatial assets for seamless client delivery and interactive viewing.
What You'll Work On
Advanced Neural Reconstruction: Design, train, and scale state-of-the-art models for dense 3D geometry extraction (e.g., Gaussian Splatting, NeRFs) across multi-GPU clusters to handle massive spatial datasets.
Sim-to-Real Integration: Reconstruct high-fidelity, physically accurate digital twins of real-world environments to provide rich spatial priors that directly improve and regularize downstream robotics pipelines, world models and other sim-to-real training.
Client Delivery & Viewer Optimization: Compress, optimize, and package massive 3D scene representations for high-framerate rendering in client-facing viewers, ensuring clients can interact with our data without sacrificing visual fidelity.
Emergent Perception R&D: Rapidly prototype new architectures to isolate dynamic actors from static environments, resolve algorithmic bottlenecks, and fuse novel hardware sensor integrations.
What You Bring
Deep expertise in 3D Computer Vision, Neural Rendering, multi-view geometry, and spatial modeling.
Proven experience training and scaling large-scale 3D vision models from scratch using PyTorch and multi-terabyte datasets.
Experience writing custom CUDA kernels to accelerate 3D operations, ray marching, or rasterization.
Strong Signals:
First-author publications in top-tier venues (CVPR, ICCV, ECCV) focusing on 3D deep learning, neural rendering, or spatial transformers.
Specific projects that include deploying 3D assets to WebGL, custom rendering engines, or optimizing splats for interactive viewing that are available publicly.
Why This Role?
The Data Advantage: Access proprietary spatial and temporal ground-truth data at a scale that most academic researchers only dream of.
High Impact: Your spatial models and environmental reconstructions will directly define how the next generation of embodied AI agents bridge the gap between simulation and the physical world.
Standard company text repeated across Mecka AI's postings is omitted here.