Perception Engineer

About the role Laelaps builds the intelligent software that powers physical security in the real world, letting robots and sensors handle dangerous and critical tasks people shouldn't have to.

As our Perception Engineer, you'll build and own the perception systems behind our multi-sensor surveillance and robotics stack, deployed on-prem with government and defence customers.

This is a builder's role, not a research role.

You'll start from the best available models, off-the-shelf where they do the job and trained in-house where they don't, and turn them into reliable, real-time systems that run on edge hardware.

Success in the first year means perception that works on live sites in all conditions, holds up under real-world constraints, and feeds the downstream autonomy and alerting the rest of the product depends on.

You'll report into the founding engineering team and work closely with our software and robotics engineers.

Responsibilities Design and ship cross-camera object re-identification (Re ID) for people and vehicles across distributed camera networks, in all light and environmental conditions.

Build high-throughput object detection and multi-object tracking pipelines that run across many simultaneous video streams.

Integrate and adapt vision-language models (VLMs) for open-vocabulary detection, scene understanding, and operator-facing situational awareness.

Own the video ingestion and streaming path (RTSP, Web RTC) from camera to model, with attention to latency, resilience, and dropped-frame handling.

Optimize and deploy models on edge hardware using Tensor RT, quantization (INT8/FP16), and pruning to hit real-time targets on Jetson and edge-class devices.

Evaluate, fine-tune, and integrate existing open-source and commercial models, and train custom models when off-the-shelf options fall short.

Partner with the software and robotics teams so perception output feeds downstream autonomy and alerting.

Qualifications

Required: 3+ years building and shipping computer vision or ML systems in production, or equivalent depth.

Strong understanding of state-of-the-art techniques for cross-camera Re ID, object detection, and multi-object tracking.

Hands-on experience with VLMs and a working grasp of the current model landscape.

Solid understanding of real-time video streaming (RTSP, Web RTC) and multi-stream pipelines.

Experience taking models from prototype to deployment on edge hardware: Tensor RT, quantization, latency tuning.

Strong Python and Py Torch (or JAX) skills, with a systems-builder mindset.

Broad ML literacy beyond vision and solid software engineering hygiene: version control, reproducibility, evaluation discipline.

Preferred: Strong data pipeline skills: curating, cleaning, labelling, and managing large image and video datasets.

Experience with NVIDIA Deep Stream.

MLOps experience: model versioning, CI/CD for ML, monitoring deployed models in the field.

Familiarity with RAG and LLM-based pipelines and integrating them into a wider system.

Background in surveillance, robotics, or safety-critical / defence systems, including on-prem or air-gapped deployment.

Publications at top venues (ICCV, CVPR, ICLR, Neur IPS) are a plus but not expected.

We value shipped systems more. #J-18808-Ljbffr