Software Engineer - Realtime Pipeline

Bridge Neurotech is seeking a Software Engineer to own and scale a real-time software pipeline for neural decoding workflows, from raw RF ingestion through ML inference and decoded outputs.

Responsibilities

• Own the end-to-end real-time path: raw RF data ingestion, beamforming, processing (including clutter filtering), ML preprocessing, model inference, and decoded output generation
• Develop and mature the ML inference engine, including:
  • Model loading from artifacts
  • GPU memory residency strategy
  • Batching approach for throughput and latency
  • Inference implementation using TensorRT/ONNX or hand-built CUDA inference
  • Kernel-level integration with upstream imaging compute
• Integrate, extend, and contribute to GPU beamforming where needed
• Meet and sustain real-time throughput and latency targets at multi-Gbit/s ingest rates, including deterministic tail latency suitable for closed-loop decoding
• Define and own the model serving contract with the ML/AI Lead, including a model update path that avoids service interruption
• Build the streaming and storage layer to support both:
  • Offline training data access
  • Real-time inference data flow
• Coordinate with team members to define upstream device acquisition interfaces and downstream BCI application interfaces
• Implement observability across all pipeline stages and create benchmarks and regression tests to maintain performance and inference correctness as the system evolves

Requirements

• BS/MS/PhD in computer science, electrical engineering, or a related field
• 8+ years building production real-time or HPC systems
• Expert-level CUDA and modern C++; experience writing or extensively modifying GPU kernels for signal processing or imaging workloads
• Proven production experience deploying ML inference on GPUs under hard latency constraints, including:
  • Transitioning trained PyTorch (or equivalent) models to deployment
  • Hands-on use of TensorRT, ONNX Runtime, Triton, or hand-built CUDA inference engines
• Demonstrated delivery of real-time data pipelines at multi-Gbit/s rates with tight latency budgets
• Strong understanding of data structures, algorithms, and relevant signal processing for imaging or RF, including:
  • Beamforming concepts
  • FFTs
  • IQ demodulation
  • SVD-based filtering
  • Autocorrelation
• Proficiency in Python and the PyTorch ecosystem to collaborate with the ML team, identify production changes, and discuss model architecture trade-offs that affect latency

Technologies

• CUDA
• C++
• PyTorch
• TensorRT
• ONNX
• ONNX Runtime
• Triton
• Python
• FFT
• IQ demodulation
• SVD-based filtering
• Autocorrelation

Benefits

• Excellent medical benefits
• 401(k) with 6% match

Nice to Have

• Experience with functional imaging or other high-data-rate imaging modalities
• Experience integrating ML inference with upstream real-time compute, including shared GPU memory layouts and minimizing host-device round-trips
• Experience with high-bandwidth I/O: GPUDirect Storage, RDMA, kernel-bypass networking, NVMe arrays

Location: Redwood City, CA (onsite)