Algorithm Engineer – REM

We’re building a lightweight 2D vector map system for intelligent driving. We adopt learning-based algorithms to reconstruct structured road layers from mass vehicle driving data. Our team leverages computer vision, graph modeling and computational geometry to build fully automated map production pipelines, with rapid iteration as our core value.

What you’ll do

1. Develop learning-based algorithms to reconstruct structured road vector data using mass crowdsourced vehicle perception records, REM and multi-modal sensor inputs.

2. Model road geometry, semantic features, lane connections and global road topology through spatial reasoning and graph networks.

3. Combine deep learning, graph modeling and computational geometry to tackle complex urban scene challenges.

4. Build scalable automated pipelines for crowdsourced data aggregation, model validation, map optimization and incremental map updates.

5. Continuously optimize model accuracy, robustness and generalization under occlusion, variable illumination and unmarked roads.

6. Write standardized, maintainable and testable production code with Python/C++, participate in code review and drive team technical iteration.

What we expect from you

1. Master or Ph.D. in Computer Science, Electronic Engineering, Robotics or related majors.

2. 3+ years’ algorithm development experience in computer vision, spatial modeling, trajectory mining or robotics.

3. Solid programming and algorithm capabilities with Python or C/C++; proficient in at least one deep learning framework (PyTorch / TensorFlow preferred).

4. Hands-on experience delivering production-level deep learning or visual perception systems.

5. Able to independently research ambiguous technical bottlenecks and deliver practical engineering solutions.

6. Fluent oral and written communication in both Mandarin and English, excellent team player.

Nice-to-have

1. Familiar with topological learning networks: MapTR, VAD, LaneGAP, TopoNet, as well as image stitching and vectorization algorithms.

2. Experience with mass vehicle trajectory aggregation and crowdsourced perception data processing.

3. Basic exposure to GIS, computational geometry, SLAM or ADAS lightweight vector map development.

4. In-depth understanding of CNN, GNN, Transformer, object detection, semantic segmentation and generative AI.

5. Proven track record of migrating academic research algorithms to mass-production pipelines.