Embedded Computer Vision Engineer (Edge Inference)

DCONSTRUCT ROBOTICS PTE. LTD.; Singapore; On-site; SGD 70,000 - 120,000; Full time

Job summary

DCONSTRUCT ROBOTICS PTE. LTD.

in Singapore is seeking an Embedded Computer Vision Engineer (Full-time/Intern) to build computer-vision capabilities on Linux-based edge devices and bring models from workstation to on-device deployment. You will develop and optimize inference pipelines, integrate vendor runtimes for NPUs/MPUs, and work near the Linux kernel to optimize performance, memory, and I/O while delivering reliable, energy-efficient embedded AI solutions.

Qualifications

• 2–3+ years of embedded software experience.
• Experience shipping Linux-based products.
• Fluent in deploying ML models on embedded systems.

Responsibilities

• Develop and optimize inference pipelines for on-device execution.
• Integrate vendor runtimes on embedded GPUs/NPUs/MPUs.
• Work close to the Linux kernel for performance, memory, and I/O.
• Collaborate to deploy models from workstation to embedded devices.

Skills

C++ (modern C++11/14/17)

Python

Embedded software development

Linux proficiency

Computer vision basics

Deep learning inference deployment

Tools

TensorRT

TFLite

OpenVINO

ONNX Runtime

Vendor NPUs/MPUs SDKs

Job description

About Us: We are a leading AI and robotics company at the forefront of technological innovation, dedicated to creatingcutting-edge solutions that revolutionize industries. As we continue to grow, we are seeking a motivated and capable Embedded Computer Vision Engineer(Full-time/Intern) to join our team.

Job Description: We are building computer-vision capabilities on Linux-based edge devices. This role owns the embedded software that takes models from “works on a workstation” to “runs reliably, efficiently,and measurably fast on-device.” You will develop and optimize inference pipelines, integrate vendor runtimes on embedded GPUs/NPUs/MPUs, and work closeto the Linux kernel when needed (performance, memory, I/O, and driver interactions).

Requirements and Skills

• 2-3+ years professional experience in embedded software development, with significant time shipping Linux-based products for Full-time applicants.
• Integrate and run deep learning models using edge runtimes/toolchains (e.g., TensorRT, TFLite, OpenVINO, ONNX Runtime, vendor SDKs for NPUs/MPUs).
• Strong expertise in C++ (modern C++11/14/17) and python (quickly deploy ML model on the embedded system).
• Working knowledge of computer vision and deep learning inference concepts (pipelines, tensors, common CV tasks, latency/accuracy tradeoffs). You do not need to be a model developer/researcher, but must be fluent in deploying and running models.
• Experience optimizing inference for edge hardware (NPUs/MPUs/GPUs/accelerators), including quantization and runtime constraints.

Preferred Qualifications

• Implement deployment-oriented model optimizations whenneeded (quantization workflows, operator compatibility fixes, graph optimizations, runtime-specific conversion).
• Work on Linux-based embedded platforms: cross-compilation, build systems, packaging, and reliable field deployment.
• Strong Linux systems knowledge, including at least some of: kernel fundamentals, device I/O, scheduling, memory behavior.