4 Gaussian Splatting Jobs

As a Computer Vision Lead at EdgeFleet.AI, you will be at the forefront of creating an unparalleled intelligence that transcends conventional boundaries. You will play a pivotal role in shaping a shared brain for autonomous systems, where drones, robots, and fleets not only operate but truly comprehend their surroundings. Your expertise will be instrumental in shaping the future of computer vision, where perception knows no limits. Beyond mere recognition, you will delve into the realms of prediction, reconstruction, and gaining profound insights into a constantly evolving world. We are looking for a visionary individual who thrives at the bleeding edge of technology, with a deep understanding of concepts like SLAM, NeRF, Gaussian Splatting, multi-view geometry, 3D reconstruction, and self-supervised learning. Your role will extend beyond mere coding, as you will be tasked with envisioning pipelines that transform pixels into endless possibilities. If you have ever envisioned teaching machines to see the unseen, developing models capable of reconstructing, interpreting, and predicting real-world dynamics, and creating vision systems that redefine the landscape of autonomous intelligence, then this opportunity is tailor-made for you. Join us at EdgeFleet.AI to not only build computer vision models but to architect the eyes of the future. Your contributions will go beyond algorithms bring your imagination, audacity, and passion to the table. Together, we will empower machines to not just see but perceive with a purpose. Don't hesitate to reach out to explore this exciting opportunity. The world is fast-paced, and so are we. Let's shape the future of AI, autonomy, and deep tech together. #EdgeFleetAI #ComputerVision #AI #Autonomy #DeepTech #OneMindAnyMachine,

Job Title: 3D Vision Engineer/Scientist Location: Vapi, Gujarat Employment Type: Full-Time Overview We are seeking a highly skilled 3D Vision Engineer/Scientist with expertise in geometry-focused computer vision. This role involves advancing systems for 3D reconstruction, depth and flow estimation, pose understanding, and scene representation through Neural Radiance Fields (NeRFs), Gaussian Splatting, and scene graphs. The position will contribute to predictive intelligence and vision-language grounding for robotics applications. Key Responsibilities Develop stereo/monocular depth and optical flow algorithms; work on 3D reconstruction and occupancy mapping. Implement kinematic pose estimation for humans and robots, enabling affordance modeling and grasp synthesis. Build 3D priors to enhance prediction, planning, and VLM grounding. Must-Haves 48+ years of experience in geometry-focused computer vision. Strong expertise in differentiable rendering and multi-view optimization. Nice-to-Haves Experience with Neural Radiance Fields (NeRFs) or Gaussian Splatting on edge devices (e.g., Jetson). Knowledge of real-time TSDF and occupancy mapping techniques. Success Metrics Depth/flow End-Point Error (EPE). Chamfer distance / Intersection over Union (IoU). Frames per second (FPS) and system latency. Grasp success rate. Domain Notes Humanoids: - Articulated object reconstruction and contact reasoning. AGVs (Autonomous Ground Vehicles): - Aisle topology and shelf modeling. Cars: - Birds Eye View (BEV) occupancy and lane topology. Drones: - Large-area photogrammetry; DSM/DTM quality. Application Instructions Interested candidates may apply by sending their resume and cover letter to [HIDDEN TEXT] with the subject line: 3D Vision Engineer/Scientist Application. Show more Show less

Join the leader in entertainment innovation and help design the future at Dolby. At Dolby, where science meets art and high tech surpasses mere computer code, your work will have a global impact, from movie theaters to smartphones. Revolutionizing how people create, deliver, and enjoy entertainment worldwide is our mission, and to achieve this, we seek top talent. Dolby provides the resources of a large corporation combined with the opportunity for individuals to truly make a difference and receive recognition for their contributions. Alongside a collegial culture, challenging projects, and competitive compensation and benefits, this role is based in Bangalore, offering a mix of office and work-from-home flexibility. Dolby's research division is currently seeking a volumetric imaging researcher to contribute to pioneering efforts in developing next-generation volumetric and spatial scene understanding and representation technologies. As a member of the Multimodal Experience Lab within Dolby's Advanced Technology Group, you will collaborate with a skilled team of researchers to advance volumetric scene representation, novel view synthesis, scene analysis and understanding, and scene rendering technologies. Your key responsibilities will involve leading research efforts beyond the current state of the art, particularly focusing on the composition and de-composition of volumetric scenes, as well as the manipulation of lighting, shadows, and occlusion. In addition to conducting fundamental research, you will be involved in technology transfer to product groups and patent application drafting. Key Responsibilities: - Conduct cutting-edge research in computer graphics and view synthesis - Collaborate with a top-notch research team to define and execute research roadmaps - Implement strong development methodology, including quality metrics and test content, to validate algorithmic solutions - Utilize AI and deep learning techniques to innovate and improve applications - Share knowledge through technical whitepapers, publications, and internal presentations - Transfer technology to product groups and contribute to patent applications - Stay informed about the latest research in computer graphics and computer vision fields Requirements: - Ph.D. in Computer Science, Electrical Engineering, Applied Math, Physics, or related fields - Demonstrated strong publication record in major conferences/journals - Proficiency in view synthesis and/or light-field research - Familiarity with scene representation methods such as Gaussian Splatting or NeRF - Experience in computer graphics and computer vision R&D - Proficiency in research-oriented programming languages (Python, Matlab, or C/C++) - Experience in building and testing models in Pytorch/Tensorflow environments - Excellent written and verbal communication skills - Ability to collaborate effectively with colleagues in research and software development - Expertise in deep learning-based solutions Nice to have: - Experience with real-time graphics (OpenGL/Cuda/DirectX/Vulkan) - Familiarity with Pytorch3D - Experience with game engines (Unreal, Unity) - Exposure to XR environments, capture, and devices,

Qualcomm is the largest fabless design company globally, providing hardware, software, and related services to mobile device manufacturers and operators worldwide. The chipsets developed by Qualcomm power a diverse range of products, including tablets, smartphones, e-readers, and various devices, with the digital design team playing a crucial role in their development. As a member of our team, you will be expected to become a subject matter expert in your technical area and serve as a go-to person for your colleagues. The dynamic work environment necessitates effective communication, meticulous planning, and efficient execution skills due to regular cross-functional collaboration. Within Qualcomm's Adreno Graphics Research Team, you will engage in research, prototyping, profiling, analysis, and optimization of cutting-edge 3D Computer Graphics algorithms. This includes exploring emerging technologies such as Ray Tracing, Mesh Shading, NERFs, and Gaussian Splatting. Collaborating at the intersection of Computer Graphics and GPU architecture, you will identify inefficiencies in existing Adreno GPU hardware and propose enhancements for the next generation of GPU HW architectural improvements. Key Responsibilities: - Develop, analyze, and optimize emerging graphics workloads. - Create functional models and microbenchmarks to gain insights into GPU hardware and provide recommendations based on analysis. - Identify and address performance bottlenecks through hardware or software optimizations. - Collaborate with HW Architects to define new features for Next Gen GPU Architecture. - Contribute to the advancement of Adreno GPU intellectual property through research publications and blogs. - Explore emerging 3D Graphics algorithms, conduct literature surveys, competitive analysis, and propose enhancements to boost Adreno GPU performance, power efficiency, and functionality. Minimum Qualifications: - Bachelor's or higher degree in Computer Engineering, Computer Science, Electrical Engineering, or a related field. - 8+ years of experience in Systems Engineering or related roles. Preferred Qualifications: - Master's or higher degree in Computer Engineering or Computer Science. - 7+ years of relevant experience in GPU System Engineering or Research.,