Software Engineer, Localization

Mach Industries; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Mach Industries is building an AI-forward autonomy stack for contested environments where GPS and sensing may be unavailable. You will design estimation and sensor-fusion algorithms powering robust navigation across product lines, working at the intersection of perception, state estimation, and embedded systems.

You will prototype and productionize vision navigation features and develop SLAM-based estimators on Linux/embedded hardware, with responsibilities spanning calibration, timing, and

Qualifications

• Proficient in modern C++ on Linux with debugging, profiling and testing discipline.
• Experience with SLAM/state estimation, EKF/UKF, factor graphs, or least-squares optimization.
• Vision-based VIO/SLAM experience, camera models, optical flow.
• Sensor fusion: IMU, GNSS/RTK, multi-camera, LiDAR, radar integration.
• 5+ years of research-to-production delivery or equivalent.
• Degree or equivalent in CS/Robotics/EE/Aerospace or related field.

Responsibilities

• Prototype and productionize vision navigation features end-to-end from sim to HITL to flight with production C++.
• Turn detections into measurement models with latencies and covariances; keep estimators reliable.
• Stabilize GNSS to VIO handover to prevent jumps and resets.
• Build and optimize real-time software on Linux/embedded; profile and vectorize code.
• Own calibration and time-sync across sensors; validate in flight.
• Create evaluation pipelines and dashboards for drift, stability, relocalization, and track quality.
• Integrate maps, magnetics, and radar for long-term consistency and loop-closure.

Skills

Modern C++ on Linux

Python tooling

SLAM/state estimation

VIO/SLAM

PyTorch (DL)

CUDA/TensorRT

Education

BS/MS/PhD in CS/Robotics/EE/Aerospace or equivalent

Tools

CUDA

TensorRT

ONNX Runtime

ROS 2

GTSAM

Ceres Solver

Jetson

Job description

Mach Industries is building an AI‑forward autonomy stack for contested environments where GPS and other sensing is unavailable or unreliable. As an member of our team, you will design and implement state-of-the‑art estimation and sensor-fusion algorithms that power robust navigation across all of our product lines. You will work at the intersection of perception, state estimation, and embedded systems to bring research‑grade algorithms to rugged, real‑world deployments.

Key Responsibilities

• Prototype and productionize vision navigation and targeting features end-to-end from sim to HITL to flight with production C++.
• Turn detections (EO/IR/RF/radar) into well‑posed measurement models with latencies/covariances; make the estimator decision‑aware without corrupting state.
• Stabilize GNSS to VIO handover (adaptive covariances, gating, hysteresis, reset‑less alignment) to eliminate jumps and estimator resets.
• Build and optimize real‑time software on Linux/embedded; profile CPU/GPU, vectorize hot paths; optional CUDA/TensorRT on Jetson hardware.
• Own calibration and time-sync across IMU/cameras/radar/LiDAR/GNSS; validate in flight.
• Create evaluation pipelines and dashboards for drift, handover stability, relocalization, track quality
• Integrate global aids (maps, magnetics, radar) for long‑term consistency and loop‑closure robustness.

Required Qualifications

• Stellar software ability: Modern C++ on Linux; Python for tooling/analysis; strong debugging, profiling, testing discipline.
• SLAM/state estimation: Error‑state EKF/UKF, factor graphs, nonlinear least‑squares (Ceres/GTSAM), observability and covariance tuning.
• Vision experience VIO/SLAM, camera models, optical flow/feature tracking; comfort with deep learning for detection/seg/pose (PyTorch) and on‑edge deployment.
• Sensor integration: IMU strapdown and biases, GNSS/RTK; multi‑camera, LiDAR, radar, magnetometer, barometer.
• Ship and fly: Proven research‑to‑production delivery and field testing on real platforms.
• 5 years of experience with either a BS/MS/PhD in Computer Science, Robotics, Electrical/Aerospace Engineering, or related field, or equivalent practical experience.

Preferred Qualifications

• Experience with CUDA/TensorRT/ONNX Runtime; NVIDIA Jetson pipelines.
• Exposure to ROS 2, PX4/ArduPilot integration
• Experience in contested/denied RF, low‑light/night, high‑vibration environments.
• Rust for systems tooling; Docker for reproducibility.

To conform to U.S. Government export regulations, applicant must be a (i) U.S. citizen or national, (ii) U.S. lawful, permanent resident (aka green card holder), (iii) Refugee under 8 U.S.C. § 1157, or (iv) Asylee under 8 U.S.C. § 1158, or be eligible to obtain the required authorizations from the U.S. Department of State. Learn more about the ITAR here.