About Human Archive
Human Archive is a research lab backed by Y Combinator focused on modeling human embodied intelligence.
Humans are the most sophisticated biological systems we have ever observed, yet we still do not fully understand ourselves. Research into human physical intelligence — including the human hand, proprioception, and vision — remains largely unsolved. Our mission is to recover human embodied intelligence as a learned model. To achieve this, we build custom hardware products, deploy them globally at scale, and publish research. Today, our data is used for robotics and world modeling, but the broader opportunity is advancing scientific research into intelligence itself.
Founded by Stanford and UC Berkeley researchers, we are lean, deeply technical, and operate at extreme speed, taking on unglamorous and conventionally impossible problems that directly unlock step-function gains in model capability.
The deployment of capable humanoids at scale will permanently redefine human labor. Undesirable physical work will disappear, and human effort will shift toward a new era of abundant creativity.
We are building the infrastructure to accelerate that transition by assembling the Human Archive mafia. You will own meaningful systems from day one and see your work directly impact model capabilities. This is a once-in-a-generation inflection point. If you want to help reshape physical labor and work on problems that matter at civilizational scale, join us.
What you'll work on
The single hardest role on the team. You'll own the entire optics and calibration stack — lens selection, image quality, intrinsics, extrinsics, ISP tuning, multi-camera alignment. End to end.
Optics and sensor selection
Lens characterization (MTF, distortion, chromatic aberration)
Sensor variant evaluation and selection
Optical mount tolerance budget with the mechanical team
IR filter and lens shading correction approach
Image quality and ISP tuning
AE, AWB, color matrix, gamma, lens shading correction
Multi-camera color and exposure consistency
Image quality validation in mixed real-world lighting
Multi-stage calibration pipeline
Camera intrinsics and fisheye distortion modeling
Stereo and multi-camera extrinsics
Camera-IMU spatial and temporal calibration
Magnetometer calibration in the assembled stack
Calibration infrastructure
Rig design and fixture builds (turntables, lighting, targets)
Calibration software pipeline
Automated verification and QA systems
Documentation for factory deployment
Production and field calibration
Factory-floor calibration procedure
Per-unit calibration QA gating
Field calibration drift monitoring
Sensor / lens transition tooling
Required technical experience
Hands-on multi-camera calibration (intrinsics, stereo, multi-rig)
Fisheye distortion modeling (Kannala-Brandt or equivalent)
IMU calibration: bias, alignment, Allan variance, temperature curves
Calibration tooling and infrastructure for production
Comfortable in both the optics lab and the calibration software stack
Strong plus
OpenCV, Kalibr, or similar calibration frameworks
ISP tuning on Qualcomm, NXP, or Ambarella platforms
AR/VR, autonomous vehicle, or research-grade capture device background
Camera-IMU temporal alignment
Manufacturing calibration line experience
Uncertainty quantification and error analysis
About this role Your work determines whether thousands of hours of captured data is usable. Bad calibration is silent — data passes acceptance and fails downstream model training months later. The candidate pool is small. We pay top of band.