We are seeking a
Senior Computer Vision / Multimodal Engineer
to design, train, and deploy advanced vision models for object detection, segmentation, tracking, and behavior analysis within real-world retail and mobility environments. You will play a key role in optimizing real-time performance for edge and cloud systems, developing robust inference pipelines, and pushing the boundaries of multimodal AI.
This is an exciting opportunity to work on
cutting-edge visual AI
that impacts real-world applications, collaborating with a highly skilled team of data scientists, engineers, and product experts.
THIS ROLE IN BASED IN
LONDON,
UK, PLEASE ONLY APPLY IF YOU ARE OPEN TO RELOCATE
Key Responsibilities
* Design, train, and deploy
Computer Vision models
for detection, segmentation, tracking, and behavior understanding.
* Optimize
inference pipelines
for real-time performance on
edge devices
(e.g., NVIDIA Jetson, Coral) and
cloud infrastructure
.
* Collaborate with
data and product teams
to define new use cases, prototype solutions, and take models from lab to production.
* Develop
synthetic data generation pipelines
and augmentation strategies to enhance robustness across lighting conditions, formats, and environments.
* Research and integrate
state-of-the-art Vision Transformers (ViTs), Large Vision Models (LVMs), and Multimodal AI
into production workflows.
* Work with
CCTV and multi-camera systems
for tracking, localization, and behavior analytics.
* Build proof-of-concept systems, perform real-world validation, and continuously improve accuracy and performance.
Requirements
* 5–7 years
of experience in
Computer Vision and Deep Learning
with deployed production models.
* Strong proficiency in
Python
and
PyTorch
; hands-on experience with
OpenCV, TensorRT, ONNX, or Triton
.
* Proven expertise in
object detection/tracking models
such as
YOLO, Deep SORT, DINOv2
, or similar.
* Experience with
real-time or low-latency processing
,
multi-threaded programming
, and
performance tuning
.
* Experience deploying and optimizing models on
edge devices
(Jetson, Coral, etc.).
* Demonstrated passion for
research, innovation, and emerging AI technologies
.
* Experience in
3D modeling
or
video behavior analytics
is a plus.
ONLY CANDIDATES WITH THE REQUIRED SKILLS AND EXPERIENCE SHOULD APPLY TO THIS JOB