This is a solutions-lead role that codes. You drive the engagement from problem to production and are a strong enough perception engineer to be trusted in front of clients and to write the code that ships. The technical spine is computer vision, perception, and 3D geometry; the surrounding robotics stack — LiDAR, calibration, sim-to-real, VLA models — is where you apply that core to real deployments. You own the "can we actually do this?" answer, and then you go build it. You are research-aware, principled in how you diagnose problems, and comfortable operating where best practices are still being defined.
RESPONSIBILITIES
Own client engagements end to end — technical discovery, solution architecture, hands-on build, and delivery — acting as the technical authority on feasibility.
Translate ambiguous real-world problems into concrete perception and robotics ML architectures; lead demos and proof-of-concept scoping.
Design and build CV and perception systems — detection, segmentation, pose estimation — on the 3D geometry underneath (SE(3), camera models, projection, coordinate frames).
Own sensor calibration and fusion — intrinsic/extrinsic, hand-eye, and LiDAR–camera — plus LiDAR processing (registration, ground segmentation, object detection).
Design egocentric data collection pipelines using wrist/head-mounted cameras, depth sensors, and IMU for robot learning.
Bridge simulation and deployment via domain randomization, sim setup, and sim-to-real gap analysis.
Evaluate, select, and integrate VLA models, and fine-tune large pretrained models under data and compute constraints.
Build supporting services — agentic loops, REST/gRPC APIs, and PostgreSQL — to expose model inference and robotics services.
Mentor engineers, drive principled decisions (diagnose before solving), and translate current research into practical client implications.
QUALIFICATIONS
Bachelor’s degree in Computer Science, Engineering, or related field
BONUS POINTS
Agentic systems and prompt engineering — tool-use agents and multi-step planners.
API development (REST/gRPC, Docker, basic CI/CD) and PostgreSQL.
ROS / ROS2 or equivalent robotics middleware.
C# for Unity-based simulation and tooling.
Fine-tuning large pretrained models under data/compute constraints.
Edge/onboard optimization — TensorRT, ONNX, quantization.
RL / RLHF, motion planning, kinematics, or URDF.
Hands-on with robot hardware (Franka, UR, Unitree, or similar).
Research orientation — tracks arXiv, forms opinions from first principles.
Publications, open-source work, or notable projects in robot learning or Physical AI.
EQUAL OPPORTUNITY EMPLOYER
At TELUS Digital, we are proud to be an equal opportunity employer and are committed to creating a diverse and inclusive workplace. All aspects of employment, including the decision to hire and promote, are based on applicants’ qualifications, merits, competence and performance without regard to any characteristic related to diversity.
We will only use the information you provide to process your application and to produce tracking statistics. Since we do not request personal data deemed sensitive, we ask you to abstain from sharing that information with us.
For more information on how we use your information, see our Privacy Policy https://jobs.telusdigital.com/pages/applicant-privacy-notice.