The Role
Own the architecture and technical direction of a production perception system for home security hardware. Build robust computer vision and machine learning pipelines for multi-camera tracking, sensor fusion, inference, and edge deployment. Improve accuracy, latency, reliability, observability, and graceful failure handling across challenging environmental conditions. Lead evaluation infrastructure, field-data feedback loops, system interfaces, technical reviews, and cross-functional collaboration with hardware, cloud, and product teams.
Summary Generated by Built In
Who We Are
Sauron is the home security company of the future. Homeowners today lack compelling options when it comes to peace of mind against vulnerabilities, and total command and control of their home; there is no definitive, protective brand in the space. Leveraging cutting-edge AI, sensor technology, and nonlethal deterrence, Sauron brings next-generation technology to homeowners to protect their families and property. Incubated by the serial entrepreneur Kevin Hartz and Atomic, Sauron has raised an $18M seed round from leading venture capital firms and angel investors, including 8VC and Flock Safety CEO Garret Langley, to build the new perception system for the home.
The Role | Senior Perception Engineer
Perception is the foundation of the Sauron product. Every decision the system makes (what to show a homeowner, what to disregard, what to escalate) depends on whether we have correctly understood what took place outside the home. We are seeking the person who will own this domain.
Our hardware operates around the home and must complete its mission reliably in all environmental conditions: at night, in adverse weather, and in the presence of occlusion and deliberate evasion. In this role, you will set the technical direction for how we achieve that, including what we sense, what we infer, which problems are best addressed through models and which through systems, and what "ready to ship" means in measurable terms rather than impressions.
You will own the perception architecture and the accuracy, latency, and cost tradeoffs that underpin it. You will work closely with the hardware team to define sensing requirements across successive product generations, and you will serve as the authority that cloud, product, and hardware teams consult to understand what perception can and cannot do. You will write a substantial amount of code, focused on the most difficult problems, but your success will be measured by whether the perception system as a whole becomes better, faster, and more trustworthy.
We Value
- Collaboration, pair programming, and teamwork.
- Taking ownership across the stack.
- Test-driven development, and refactoring regularly to keep our codebases healthy.
You Will Contribute By
- Evolving the pipeline architecture so cameras can come and go, and configuration can change, without disrupting live video or losing object identity.
- Setting the boundary between systems and models. You decide what belongs in the compiled service, what belongs in the inference graph, and where the performance ceiling really is.
- Owning perception quality end to end. Defining what good looks like in numbers: evaluation data, a regression harness, and a defensible story on model choice for our hardware.
- Extracting the maximum value from our sensors. Fusing every observation available while staying robust to occlusion, poor lighting, and deliberate evasion.
- Taking the service from "runs" to "trustworthy unattended." Failure detection, graceful degradation, and observability good enough that we know why something broke without a site visit.
- Closing the loop from the field. Using deployment data to find headroom, and building the dataset and evaluation infrastructure that makes that repeatable.
- Leading the work and the people. Setting direction across perception, reviewing the hard changes, and owning the interfaces perception exposes to the rest of the product.
Your Background Includes
- Around 5+ years building production systems, with several at staff scope: owning a system's architecture, not just its tickets.
- Significant professional experience with perception or machine learning for hardware products in a safety-critical field - aerospace, robotics, medical devices, autonomous vehicles, or physical security.
- Deep modern C++. This is a C++20 codebase with Abseil, gRPC, and CMake; you should be comfortable owning lifetime, threading, and shutdown semantics in a long-running daemon.
- Real GStreamer or media-pipeline experience: pads, probes, caps negotiation, bus messages, and the specific pathology of a pipeline that is alive but not moving. DeepStream or another NVIDIA video stack is a strong plus.
- Applied computer vision you have shipped - multi-object tracking, re-identification, or multi-camera association - and the judgment to know when the answer is a better model versus better geometry versus better plumbing.
- A clear grasp of linear algebra, optimization, statistics, and algorithms, and the theory behind the techniques you reach for.
- Experience across the deep-learning lifecycle: PyTorch or an equivalent framework, custom layers and operations, optimizing networks for inference on edge compute, reproducibility, and honest evaluation.
- GPU inference in practice: TensorRT engines, batching, fp16, and reasoning about where latency actually goes.
- Edge instincts. You have debugged something that only fails on the device, after nine hours, on one customer's network, and you treat observability and failure classification as part of the feature.
- Python fluency. A meaningful share of the load-bearing logic is Python, and you will be the one deciding what it costs us.
- A generalist mindset - able to dive in wherever the bottleneck is, from cloud training infrastructure down to embedded systems.
- Excellent written and verbal communication, and the ability to set technical direction and disagree productively with adjacent teams.
Nice to Have
- NVIDIA Jetson in production - JetPack, L4T, Yocto images, or the joy of cross-building for aarch64.
- Previous experience building multi-camera tracking systems.
- Video surveillance, VMS, or ONVIF/RTSP integrations, and knowing how cameras actually misbehave.
- GPU architecture and CUDA programming.
- Familiarity with VLMs and other multi-modal models for semantic scene understanding.
- Owning model evaluation: datasets, metrics, and the discipline to reject a model that benchmarks better but ships worse.
Compensation: $220-260k + equity + benefits
The base pay range for this role is $220,000 – $260,000 per year.
Skills Required
- Around 5+ years building production systems, including experience at staff scope owning system architecture
- Significant professional experience with perception or machine learning for hardware products in a safety-critical field such as aerospace, robotics, medical devices, autonomous vehicles, or physical security
- Deep modern C++ experience, including C++20, lifetime management, threading, and shutdown semantics in long-running daemons
- Production experience with GStreamer or media pipelines, including pads, probes, caps negotiation, and bus messages
- Applied computer vision experience shipped to production, including multi-object tracking, re-identification, or multi-camera association
- Strong understanding of linear algebra, optimization, statistics, algorithms, and the theory behind applied techniques
- Experience across the deep-learning lifecycle, including PyTorch or equivalent frameworks, custom operations, edge inference optimization, reproducibility, and evaluation
- Practical GPU inference experience with TensorRT engines, batching, fp16, and latency analysis
- Experience debugging edge-device failures and implementing observability and failure classification
- Fluency in Python
- Ability to work across cloud training infrastructure and embedded systems
- Excellent written and verbal communication and ability to set technical direction across teams
- NVIDIA Jetson production experience, including JetPack, L4T, Yocto images, or cross-building for aarch64
- Experience building multi-camera tracking systems
- Video surveillance, VMS, ONVIF, or RTSP integration experience
- GPU architecture and CUDA programming experience
- Familiarity with vision-language models and other multimodal models
- Experience owning model evaluation, datasets, and metrics
Am I A Good Fit?
Get Personalized Job Insights.
Our AI-powered fit analysis compares your resume with a job listing so you know if your skills & experience align.
Success! Refresh the page to see how your skills align with this role.
The Company
What We Do
Meet your home operating system. Home security should reinforce your peace of mind. You deserve a sanctuary, one that gives you the freedom to live your life with the people that matter most. That’s why we created something entirely new. Sauron is an autonomous platform for the perimeter of your home. It works discreetly in the background to reliably identify potential threats in all environmental conditions and it instantly recognizes who’s part of your inner circle. We provide a bespoke white-glove service, ensuring that each client’s security platform is installed with precision and care, swiftly and without disrupting the comfort or aesthetics of their home. To complement the technology, Sauron leverages its Intelligent Response and Intrusion Suppression (IRIS) Command Center, staffed 24/7 by exceptionally trained agents with diverse backgrounds in law enforcement, military service, executive protection, and other critical security fields. The team builds relationships with local police departments to ensure a rapid police response to verified security incidents.
