Full Time Robotics Software Engineer Jobs, in SGInnovate - Maukerja

This role is posted on behalf of Polybee, a startup supported by SGInnovate.

Background

Polybee is reducing uncertainty in fresh produce agriculture with autonomous pollination and yield forecasts using drones and AI. This can unlock over $20B+ in value to farmers through increased yields and reduced waste. Polybee’s autonomous drone pollination can improve yields by up to 20% while accurate forecasts improve profitability through efficiency in harvesting and informed pricing. Polybee’s product is already live and scaling up at the biggest growers in ANZ, and they're now making progress with multiple fresh produce giants in the US. Polybee is a Singapore and Melbourne-based startup backed by Temasek Foundation, SEEDS Capital, elev8 VC among others.

Job scope

You’ll be our: Robotics Engineer

You’ll be based at: Singapore HQ

You’ll be aligned with: VP Engineering

You’ll be a member of: Product Engineering

What you’ll do at Polybee

• Build and productionize onboard autonomy for our drone fleet — localization, mapping and obstacle detection/avoidance — so drones can navigate safely through complex, cluttered crop and orchard environments rather than relying solely on pre-planned waypoints.
• Design and implement visual/inertial localization pipelines (e.g. visual-inertial odometry, SLAM or equivalent) that fuse camera, IMU and other onboard sensor data for robust position estimation in GPS-degraded or visually repetitive environments.
• Develop real-time obstacle detection and avoidance algorithms — depth estimation, occupancy mapping, path replanning or equivalent — engineered to run within the compute, power and latency budget of an onboard companion computer.
• Integrate autonomy modules with the drone’s flight controller and mission-planning stack, working closely with flight software so perception outputs translate into safe, reliable in-flight decisions.
• Own the full pipeline end-to-end — from sensor data capture through algorithm design, on-device optimization, field testing and iteration — closing the loop between bench/simulation testing and real flight results.
• Partner with the computer vision and flight-planning teams to align localization and obstacle avoidance behavior with mission requirements, ensuring outputs are consistent with our existing flight-planning and imaging pipelines.
• Instrument autonomy systems with logging, telemetry and evaluation metrics (e.g. localization drift, false-positive/false-negative obstacle detections, time-to-avoid) to track performance and drive continuous improvement.
• Test extensively in both simulated and real-world field conditions across varied crop, lighting and terrain scenarios, and work with operations to diagnose and resolve issues surfaced during live deployments.
• Help establish and enforce a quality-first code culture: unit/integration tests, code reviews and CI/CD, for autonomy software running on safety-critical flight hardware.

Here's what we're looking for:

• 2–4 years building and shipping robotics or autonomy software in production or rigorously field-tested research settings, ideally on aerial or other mobile robotic platforms
• Strong programming skills in C++ and Python, with hands-on experience in computer vision and robotics libraries/frameworks (e.g. OpenCV, ROS/ROS2 or equivalent)
• Practical experience with localization and mapping techniques — visual/inertial odometry, SLAM, sensor fusion (e.g. Kalman or particle filters) or equivalent — with solid grounding in the underlying geometry, state estimation and probability
• Experience building real-time perception pipelines for obstacle detection and avoidance using cameras, depth sensors or equivalent, under real hardware constraints (compute, power, latency)
• Hands-on experience working with NVIDIA Jetson or similar embedded/companion computing platforms, and optimizing algorithms to run within their resource budgets
• Familiarity with drone flight-control concepts — flight controllers, mission/waypoint systems, coordinate frames — though prior experience specifically with DJI hardware is not required
• Ability to test and validate systems in the field, methodically diagnose failures from telemetry and logs, and iterate quickly based on real-world results
• Good communication skills and comfort collaborating closely with computer vision, flight-planning and operations teams
• Technical exposure to 3D reconstruction, photogrammetry or structure-from-motion will be highly valued
• Experience creating IP — whether in the form of patent filings, conference papers, or proprietary research — will be highly valued

Interested applicants may apply directly to DTC at: **************************-226268169f26?tab=DETAILS