Realtime Pipeline Engineer

About Bridge Neurotech

Bridge Neurotech is building a non-invasive functional ultrasound imaging (fUSI) platform with AI-based neural decoding for brain-computer interface applications. We are a seed-stage neurotechnology company developing technology that has the potential to transform how we interact with the human brain.

About the Role

We are looking for a Realtime Pipeline Engineer to own the realtime system that runs from raw multi-Gbit/s RF data off the probe all the way to decoded outputs from our neural decoding model — beamforming, imaging preprocessing, and ML inference, all in one tightly coupled latency budget. The inference latency budget is tightly coupled to the imaging pipeline latency budget: they share GPU, share memory, share the data stream. This role owns the entire realtime path and is accountable for it as one system.

Given the neural decoding model, you turn it into a production realtime decoder, sitting on top of the imaging pipeline you have also built. We build from open primitives like the Mach beamformer (https://github.com/Forest-Neurotech/mach), and you provide the technical leadership and strategy to mature the system: what to extend, what to replace, and what to push upstream.

You will work closely with our ML/AI Lead on the model serving boundary, our Embedded Systems Engineer on the data handoff from the probe, our Imaging Scientist on the imaging pipeline itself, and our Applications Engineer on the decoded output handoff downstream.

What You’ll Do

• Own the end-to-end realtime path: raw RF data ingestion, beamforming, processing (e.g., clutter filtering), ML preprocessing, model inference, and decoded output.

• Set the technical direction for the realtime stack and represent it in architecture decisions across the company

• Build the ML inference engine: model loading from artifacts, GPU memory residency, batching, TensorRT/ONNX or hand-built CUDA inference, and kernel-level integration with the upstream imaging compute.

• Integrate, extend, and, where appropriate, contribute to GPU beamforming.

• Hit and hold realtime throughput and latency targets at multi-Gbit/s ingest with deterministic tail latency suitable for closed-loop decoding.

• Define and own the model serving contract with the ML/AI Lead and the path for model updates without service interruption.

• Build the streaming and storage layer that serves raw and processed data to both offline training and realtime inference.

• Collaborate with other team members to define the upstream interface to the device acquisition layer and the downstream interface to the BCI applications layer.

• Build observability into every stage and develop benchmarks and regression tests that lock in both pipeline performance and inference correctness as the system evolves.

Who You Are

Required

• You have built and owned production realtime or HPC systems that other engineers depended on, and you’ve been the person accountable when latency targets were missed.

• Expert-level CUDA and modern C++; experience writing or extensively modifying GPU kernels for signal processing or imaging workloads.

• Demonstrated experience building production ML inference systems: taking trained PyTorch (or equivalent) models to deployment on GPUs under hard latency budgets. Hands-on with TensorRT, ONNX Runtime, Triton, or hand-built CUDA inference engines.

• Demonstrated experience building realtime data pipelines at multi-Gbit/s rates with tight latency budgets.

• Strong grasp of data structures, algorithms, and the signal processing stack relevant to imaging or RF: beamforming concepts, FFTs, IQ demodulation, SVD-based filtering, autocorrelation.

• Proficiency in Python and the PyTorch ecosystem sufficient to collaborate with the ML team, identify what needs to change for production, and have informed conversations about model architecture trade-offs that affect latency.

• BS/MS/PhD in computer science, electrical engineering, or a related field, with 8+ years work experience.

Nice to Have

• Experience with functional ultrasound or other high-data-rate imaging modalities.

• Experience integrating ML inference with upstream realtime 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.

What We Offer

• The opportunity to shape a role and a team from the earliest stages.

• Dedicated access to the probe, GPU rig, and clinical data.

• Direct collaboration with leading clinicians and neuroscientists at top-tier academic institutions.

• Competitive salary and meaningful equity.

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

Bridge Neurotech is an equal opportunity employer. We encourage candidates of all backgrounds to apply.