How to Start Working with Us
Four bounded entry offers, each with defined scope, duration, and deliverables. All four can begin remotely: hardware can be shipped to us or accessed via SSH/VPN. Start with the Measurement Baseline as the lowest-risk way to establish what you are working with before committing to a larger engagement.
Four bounded entry points, each delivering a measurable output within a defined scope. Start with a measurement baseline to get the actual numbers, or a feasibility assessment to determine whether your task is viable on your hardware before committing resources. Scope is confirmed after a technical call.
How hardware access works: Clients may ship a device to our bench, provide SSH or VPN access to hardware already in their facility, or we procure a matching target locally where that is more practical. For Deployment Engineering, on-site delivery is available by arrangement. We confirm the hardware access method before work begins.
Measurement Baseline
Full characterization of an existing vision system on its target hardware. This is the default first engagement, the lowest-risk way to know what you are actually working with before committing to optimization or redesign. Delivered remotely: hardware shipped to us or accessed via SSH/VPN.
- Latency distribution: p50, p95, p99, max
- Power draw from sustained-window sampling
- Thermal throttling behavior under load
- Claim-to-file manifest (numbers linked to raw logs)
- Verifier script for independent reproduction
- Honest limitations section
- Access to your target hardware (physical or remote)
- The model or pipeline to be measured
- Your latency and power budget targets
Feasibility Assessment
Go/no-go on "can this run on this hardware, at this accuracy?" with measured trade-off curves. Not estimates. Use this before you commit capital to a hardware choice, a training run, or an architecture. Delivered remotely; hardware shipped or accessed via SSH/VPN.
- Accuracy-vs-latency trade-off curves, measured on device
- Architecture options ranked against your constraint
- Power and thermal envelope assessment
- Risk and gap identification
- Recommended path with evidence rationale
- Go/no-go recommendation with supporting data
- Your target hardware (or agreed proxy)
- Accuracy and latency requirements
- Candidate model(s) or architecture brief
Deployment Engineering
Make the system meet its production budget: TensorRT, ONNX, JetPack, pipeline engineering, and validation under sustained load and real thermal conditions. Delivered when a working prototype exists but has not yet met its production requirements. Primarily remote; on-site available by arrangement.
- TensorRT or ONNX engine with verified export
- Inference pipeline, profiled and optimized
- Thermal and sustained-load validation report
- Before/after measurement comparison
- Integration documentation and deployment guide
- Verification and acceptance test protocol
- A working prototype or trained model
- Access to target production hardware
- Clear performance targets (latency, power, accuracy floor)
Model Development Under Constraint
Build or adapt a vision model to fit a hardware budget: measured first, designed second. Architecture, quantization, and pruning decisions are made against real numbers from your target device, not from paper estimates. Delivered remotely; target hardware shipped or accessed remotely.
- Trained or adapted model meeting measured constraint
- Quantization and pruning strategy documentation
- Full benchmarking report on target hardware
- Accuracy-latency-power trade-off analysis
- Model artifacts, training code, and export scripts
- Deployment-ready engine for your target runtime
- Target hardware platform confirmed
- Dataset or access to data collection pipeline
- Accuracy, latency, and power requirements