Overview
We're hiring a Senior Applied Research Engineer to push the frontier of reality capture. You'll take modern 3D reconstruction approaches — gaussian splatting, foundation 3D models like MASt3R and VGGT, learned depth — beyond their academic comfort zone and into our production pipeline. The lever you'll have here is rare: one of the industry's largest datasets of real-world reality capture imagery, the scale to train and adapt models on it, and the engineering culture to ship the results to customers. This is an IC role focused on applied research that ships — designing, training, and deploying models that run in production, not writing papers.
We're a small, high-leverage team behind an industry-leading photogrammetry platform. Our customers have mapped over 150M acres across more than 180 countries — one of the largest real-world reality capture datasets anywhere — across industries as diverse as construction, agriculture, mining, conservation, forestry, and infrastructure inspection. That scale and diversity is the moat: it's where modern 3D models meet real conditions that academic benchmarks don't capture, and where the hard engineering happens.
What matters most is real experience with modern reality capture — you have hands-on depth in either gaussian splatting or foundation 3D reconstruction (MASt3R / VGGT-class), and you've built and shipped 3D reconstruction systems in industry settings, whether at scale in production or in a focused startup environment. Experience training or fine-tuning these models on real-world data is a strong plus — that's a meaningful part of the work here. The frontier of the field is moving fast, and this role exists because we want someone who can push our pipeline forward on the modern stack and turn academic models into production-grade reality capture.
Work Environment
Work Model: Remote (work from home), with a strong preference for candidates who live in or can overlap substantially with Pacific Time.
Travel: Occasional travel (approximately 2–3 times per year) for team and company offsites, technical planning sessions, and in-person collaboration.
AI tooling: Daily use of advanced AI coding agents is expected. You'll be an active participant in the team's AI-first workflows — authoring reusable skills, evaluating tools against real problems, and holding agent-generated code to the same standard as human-written code.
Responsibilities
Design, train, evaluate, and ship 3D reconstruction systems across our pipeline — gaussian splats, foundation 3D models, SfM, MVS, monocular depth, mesh reconstruction.
Drive integration of modern reality capture approaches (splatting, foundation models) into our production stack — making the calls on what's ready to ship and what isn't.
Own the hardest technical investigations in your area, from initial triage through production rollout and long-tail support.
Optimize 3D systems for speed, accuracy, and efficiency at production scale.
Use the right tool for the problem — classical 3D computer vision when it wins, learned approaches when they win.
Stay current with 3D vision research and evaluate promising techniques against our workflows.
Hold a high technical bar for your own work — high-quality designs, well-tested code, production-ready ship habits.
Contribute to the team through code review, pairing, and design feedback.
Codify debugging and investigation playbooks into reusable skills.
Use AI tools daily across the SDLC, with judgment on where they help and where they don't.
Author agent skills or tooling that other engineers use; contribute to the team's shared skills library.
Conduct rigorous evaluations of new AI tools and bring useful patterns to the team.
Review agent-generated code with the same rigor as human-written code.
Track the AI tooling landscape and bring useful patterns to the team.
Requirements
Bachelor's, Master's, or PhD in Computer Science, Engineering, or a related field, with 5+ years of professional experience in 3D Computer Vision or 3D Machine Learning, or a PhD in Computer Vision, Machine Learning, or a closely related discipline.
Hands-on experience with modern reality capture — specifically, gaussian splatting and/or foundation 3D reconstruction models (MASt3R, VGGT, or comparable). At least one of these from real hands-on work (production, startup, or other industry experience), not just paper familiarity.
Demonstrable track record of building and shipping 3D reconstruction systems — in production, at a startup, or in another applied industry setting (not just research or prototype work).
Deep experience across the broader 3D perception toolkit — at least three of: feature detection and matching, SfM, MVS, monocular depth estimation, mesh reconstruction, SLAM. Published research or open-source contributions in any of these areas is a plus.
Comfort across the classical-vs-learned spectrum — you reach for the right tool, not the trendiest one.
A real track record with agentic development.
Strong C++ proficiency — much of our photogrammetry pipeline runs in C++ and you'll be working in it daily.
Strong ability to timebox experiments, iterate effectively, and triage routes to success when the path isn't obvious.
Fluency in modern ML frameworks (PyTorch, TensorFlow, or equivalent) and modern training stacks.
Ability to work as an effective remote engineer with AM standup overlap with PST.
Strong written and verbal communication; you can take a technically dense investigation and make it land with PMs, leadership, and other engineers.
Open-source agent skills, plugins, or prompts that others use.
Experience running and monitoring many concurrent ML experiments in cloud environments.
Comfort with cloud training and inference (AWS, GCP, Azure) and containerization (Docker, Kubernetes).
Experience with geospatial systems or aerial imagery pipelines.
