Perception Engineer

Mach
San Francisco
Workplace: OnsiteFull timeUSD 125,000 - 220,000 annuallyFunction: Data Science & Machine LearningExperience: 7+ yearsSkills: ["Rigorous testing","Performance optimization","Documentation","Root-cause analysis","Generalization"]

Design, train, and deploy vision and multi-sensor perception systems for autonomous defense in GPS-denied environments. Build detection/segmentation/tracking architectures, scale foundation datasets and training recipes, and develop robust training/evaluation pipelines with continuous regression testing. Optimize models for real-time embedded inference on Jetson-class hardware using TensorRT/ONNX Runtime, and implement multimodal fusion using radar/LiDAR/RF cues. Validate with simulation and real flight data, and deliver tools for triage and drift detection.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Mach
Mach
2 weeks ago

Perception Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 5 hours agoStatus: Live
Reposted: similar role first listed 4 months ago

Job Summary

Design, train, and deploy vision and multi-sensor perception systems for autonomous defense in GPS-denied environments. Build detection/segmentation/tracking architectures, scale foundation datasets and training recipes, and develop robust training/evaluation pipelines with continuous regression testing. Optimize models for real-time embedded inference on Jetson-class hardware using TensorRT/ONNX Runtime, and implement multimodal fusion using radar/LiDAR/RF cues. Validate with simulation and real flight data, and deliver tools for triage and drift detection.
Location: San Francisco
Workplace: Onsite
Employment Type: Full time
Job Function: Data Science & Machine Learning
Seniority: Mid level

Key Responsibilities

  • •Build and refine detection/segmentation/tracking architectures for EO/IR and multi-spectral imagery, including dataset scaling and robust generalization.
  • •Stand up training and evaluation pipelines with metrics (PR/ROC, mAP, latency, robustness) and implement continuous regression testing and model-update loops.
  • •Optimize models for real-time embedded inference on Jetson-class hardware using quantization/pruning and runtime tools; profile CPU/GPU to meet throughput/latency targets.
  • •Fuse vision outputs with auxiliary sensing (radar/LiDAR/RF) for confirm/deny, association, and track management using decision-level fusion.
  • •Develop visualization, triage, and root-cause tools; instrument health metrics, drift detection, and graceful degradation; define end-to-end test plans and validate using simulation and real flight logs.

Pay and Benefits

Salary: USD 125,000 - 220,000 annually
Perks:Health InsuranceDentalVision401kPaid LeaveLearning Budget

Key Requirements

  • •Production C++ on Linux and Python for ML/tooling, with profiling, optimization, and rigorous testing discipline.
  • •Experience with CUDA backends for performance optimization and debugging.
  • •Strong experience with modern detection/segmentation/tracking models and PyTorch training/fine-tuning.
  • •Proven experience building large datasets (labeling/QA, augmentation, experiment tracking, reproducible training).
  • •Hands-on model compression and runtime optimization (INT8/FP16), meeting real-time constraints with EO/IR imagery and flight/test data.
Experience:7+ yearsDefense technologyComputer visionMultimodal perceptionPyTorchMLOps
Education:
Skills:Rigorous testingPerformance optimizationDocumentationRoot-cause analysisGeneralization
Languages:English
Tech Stack:C++LinuxPythonCUDACNNTransformerRetinaFCOSDETRMask2DPyTorchTensorRTONNX RuntimeJetsonSQLParquetRadarLiDARRFEO/IR

Eligibility

Nationality:US National

Company Brief

Mach
Designs and manufactures unmanned systems, tactical engines, and decentralized defense manufacturing infrastructure (Forge) to scale production of autonomous aerial systems and related propulsion for U.S. defense customers and partners.
Industry: Defense Manufacturing
Company Size: Medium (51 to 250 employees)
Growth: Growth Stage Startup
Valuation: USD 250M to 500M
Funding: Series B
Headquarters: Huntington Beach, United States
Founded: 2023
Glassdoor
Glassdoor: 3.9
WebsiteLinkedInGlassdoor