Research Scientist, SLAM & VIO

About Mecka AI

Mecka AI is building the data infrastructure layer for robotics and embodied AI.

We partner with leading AI labs and robotics companies to deliver high-quality, real-world datasets used to train, evaluate, and deploy robotic systems — where model performance is dictated by data quality.

The Role

We are hiring a Research Scientist (SLAM & Visual-Inertial Odometry) to build and validate state estimation systems that work in the real world, on messy sensors, under tight compute and reliability constraints.

This role is research-heavy but production-minded. You will ship algorithms that survive scale, long runtimes, and operational edge cases.

A core part of the role is expertise in Structure-from-Motion (SfM) and scene reconstruction, spanning both feed-forward and optimization-based approaches to produce high-quality 3D representations from real-world capture data.

What You'll Work On

Monocular Visual(-Inertial) Odometry (Online)

• Develop robust monocular VO/VIO pipelines (feature-based and/or learned) with strong failure detection and recovery

• Address scale ambiguity with inertial fusion, motion priors, and consistency constraints

• Optimize for low latency, bounded memory usage, and stable tracking across:

  • Challenging lighting conditions

  • Motion blur

  • Rolling shutter effects

  • Dynamic environments

Monocular SLAM (Offline / Batch)

• Build offline reconstruction pipelines for long trajectories

• Implement:

  • Global bundle adjustment (BA)

  • Loop closure at scale

  • Map optimization

• Produce high-quality trajectories and sparse/dense maps for downstream data products

• Design evaluation tooling, including:

  • Drift decomposition

  • Per-segment error analysis

  • Systematic bias detection

Stereo Visual(-Inertial) Odometry (Online)

• Implement stereo VO/VIO systems with robust calibration handling:

  • Intrinsics

  • Extrinsics

  • Temporal synchronization

• Improve depth reliability across challenging scenes:

  • Low texture

  • Repetitive patterns

  • Specular surfaces

• Optimize for stability and long-duration operation

• Build relocalization and graceful degradation mechanisms

Stereo SLAM (Offline / Batch)

• Develop large-scale mapping and trajectory refinement pipelines using stereo constraints

• Implement:

  • Loop closure

  • Global pose graph optimization

  • Uncertainty-aware optimization

• Produce maps that are:

  • Consistent

  • Repeatable

  • Operationally useful

  • Accompanied by meaningful quality metrics

Structure-from-Motion & Scene Reconstruction

• Apply and extend state-of-the-art SfM methods across two paradigms:

Feed-Forward Pointmap Regression

Examples include:

• FAST3R

• VGGT

• DA3

Focus areas:

• Fast reconstruction

• Generalizable scene geometry

• Multi-view image collections

• No per-scene optimization requirements

Per-Scene Differentiable Optimization

Examples include:

• ACE0

• FlowMap

• DROID-W

Focus areas:

• Scene-specific reconstruction

• Differentiable optimization

• Iterative refinement pipelines

Dense Scene Reconstruction

• Produce high-quality dense reconstructions using:

  • NeRF

  • Gaussian Splatting

• Build photorealistic scene representations

• Integrate reconstruction outputs into downstream data products:

  • Annotated frames

  • Spatial QA systems

  • Training signals for embodied AI models

• Benchmark reconstruction quality across:

  • Scenes

  • Sequences

  • Sensor configurations

• Define and enforce reconstruction release criteria

Common Themes

Sensor Modeling & Calibration

• Rolling shutter correction

• Time offset estimation

• IMU noise and scale-factor modeling

• Temperature-driven drift compensation

Robustness Engineering

• Automatic recovery and reset systems

• Outlier rejection

• Failure diagnostics and debugging workflows

Metrics & Evaluation

• Design evaluation suites

• Curate failure-case datasets

• Define quantitative release gates

Who You Are

Required Background

• Strong experience in SLAM, VO, or VIO research and development

• Demonstrated history of shipped systems and/or publishable research

• Deep understanding of:

  • Nonlinear least squares

  • Factor graphs

  • Filtering and smoothing

  • Uncertainty estimation

• Strong SfM experience, including:

  • Feed-forward pointmap regression approaches (FAST3R, VGGT, DA3)

  • Per-scene differentiable optimization methods (ACE0, FlowMap, DROID-W)

• Practical experience with dense reconstruction systems:

  • NeRF

  • Gaussian Splatting

• Strong C++ skills

• Comfortable using Python for research and evaluation workflows

Strong Signals

• Built systems that run reliably for hours or days in production environments

• Deep understanding of real-world sensor failure modes:

  • Calibration drift

  • Synchronization failures

  • Rolling shutter artifacts

  • Motion blur

  • Low-light conditions

• Experience with:

  • GTSAM

  • Ceres

  • Similar optimization toolchains

• Strong intuition for optimization, numerical methods, and system stability

• Experience deploying NeRF or Gaussian Splatting systems at scale

Nice to Have

• Experience with learned front-ends or back-ends:

  • Learned features

  • Learned depth estimation

  • Learned relocalization

  • Hybrid classical + ML systems

• Experience building offline mapping and large-scale batch optimization systems

• Familiarity with embedded or edge deployment constraints

• Contributions to or deep familiarity with open-source projects such as:

  • MASt3R

  • gsplat

  • nerfstudio

Why This Role

• Work on state estimation and scene reconstruction systems that directly impact real-world robotics data capture and downstream model performance

• High ownership across research, engineering, and operations

• Define the quality bar for systems deployed in production

• Access to challenging real-world datasets and large-scale capture infrastructure

• Help shape the future of robotics data, mapping, and embodied AI systems at scale

Compensation Range: $200K - $250K