Specter Ai · 3 months ago
Software Engineer - ML Infrastructure
San Francisco
Full-time
Onsite
Mid, Senior LevelSpecter is creating a software-defined control plane for the physical world, focusing on protecting American businesses through advanced sensing technology. The role involves building and scaling machine learning systems for real-time perception and inference, with responsibilities including designing scalable ML training pipelines and optimizing models for deployment on edge devices.
Responsibilities
Designing and implementing scalable ML training pipelines for computer vision models (object detection, tracking, classification, segmentation)
Building efficient model serving infrastructure for real-time inference on edge devices with constrained compute and power budgets
Optimizing models for deployment on embedded hardware (quantization, pruning, TensorRT, ONNX, CoreML)
Developing continuous training and evaluation systems to improve model performance from production data feedback loops
Creating data pipelines for ingesting, labeling, versioning, and managing massive multi-modal sensor datasets (video, radar, lidar, thermal)
Implementing model monitoring, A/B testing frameworks, and performance analytics for deployed perception systems
Collaborating with perception researchers to transition models from research to production at scale across thousands of edge nodes
Building tools and infrastructure for distributed training, hyperparameter optimization, and experiment tracking
Qualification
Required
Designing and implementing scalable ML training pipelines for computer vision models (object detection, tracking, classification, segmentation)
Building efficient model serving infrastructure for real-time inference on edge devices with constrained compute and power budgets
Optimizing models for deployment on embedded hardware (quantization, pruning, TensorRT, ONNX, CoreML)
Developing continuous training and evaluation systems to improve model performance from production data feedback loops
Creating data pipelines for ingesting, labeling, versioning, and managing massive multi-modal sensor datasets (video, radar, lidar, thermal)
Implementing model monitoring, A/B testing frameworks, and performance analytics for deployed perception systems
Collaborating with perception researchers to transition models from research to production at scale across thousands of edge nodes
Building tools and infrastructure for distributed training, hyperparameter optimization, and experiment tracking
Preferred
Strong experience with ML frameworks (PyTorch, TensorFlow) and model optimization tools (TensorRT, ONNX Runtime, OpenVINO)
Deep understanding of computer vision architectures and their deployment tradeoffs (YOLO, transformers, CNNs, real-time detection/tracking)
Hands-on experience deploying models on edge devices (NVIDIA Jetson, ARM processors, or similar embedded platforms)
Expertise building MLOps infrastructure — experiment tracking (Weights & Biases, MLflow), feature stores, model registries, CI/CD for ML
Experience with distributed training frameworks (PyTorch DDP, DeepSpeed, Ray) and GPU cluster management
Strong software engineering skills in Python and systems languages (C++, Rust) for performance-critical inference code
Familiarity with video processing, sensor fusion, or multi-modal perception systems is a plus
Prior experience in robotics, autonomous systems, or real-time ML applications is highly valued
Company
Specter Ai
Revolutionising the legal industry
2-10 employeesFunding
Current Stage
Early StageCompany data provided by crunchbase