We're looking for an experienced Staff Software Engineer who's passionate about building and optimizing real-time systems that process massive volumes of video and sensory data for AI applications. You'll design, implement, and lead the development of high-performance infrastructure that enables ultra-low latency processing, ensures reliability at scale, and powers cutting-edge AI models. You'll be at the forefront of creating the technical foundation for Perceptron's next generation of physical AI systems.

You will:

• Architect real-time data processing pipelines capable of handling petabytes of video and sensor data
• Develop high-performance inference systems that meet strict latency requirements (sub-millisecond)
• Design fault-tolerant distributed systems for AI model serving with 99.99% availability
• Optimize data streaming platforms to support concurrent processing of thousands of video streams
• Create adaptive sampling techniques to efficiently process multi-modal sensory inputs
• Implement real-time analytics capabilities to provide immediate insights from processed data

Our Stack

• Languages: Rust, C++, Python, Go
• Infrastructure: Kubernetes, AWS/GCP, Terraform, Docker
• Real-time Processing: CUDA, OpenCL, TensorRT, ONNX Runtime
• Streaming: Kafka, Flink, Redis Streams, gRPC
• Databases: ClickHouse, TimescaleDB, ScyllaDB
• ML/AI: PyTorch, JAX, NVIDIA Triton, TensorFlow Serving

You'll be a great fit if...

• You have 8+ years of software engineering experience with 3+ years focused on real-time systems
• You've built systems that process high-volume streaming data with strict latency requirements
• You're experienced with performance optimization, profiling, and distributed system design
• You understand computer vision pipelines and AI model inference optimization