Senior Perception Data Engineer - Build Scalable ML Pipelines

driveblocks; Deutschland; Remote; USD 115,115 - 172,672; Full time

Benefits offered by this job

Virtual Stock Option Plan

Job summary

driveblocks develops off‑road ground autonomy systems. We seek an Expert Perception Data Engineer to scale data workflows for robust autonomous performance in challenging conditions.

You will own the full data lifecycle from ingestion to validation, building scalable perception pipelines and embeddings-based retrieval. You will work with multimodal sensor data (camera, lidar, radar) and drive automation around data operations, with a strong ownership mindset in a fast-moving engineering

Qualifications

• 6+ years building large-scale data processing systems for ML/robotics.
• Strong software engineering in Python and/or C++.
• Experience with multimodal sensor data (camera, lidar, radar).
• Familiar with dataset management tooling, embeddings, vector databases, semantic retrieval, and similarity search.
• Ownership mindset and ability to work independently in a fast-moving environment.
• Strong communication across engineering and customer-facing teams.
• Degree in computer science, robotics, engineering or related field.

Responsibilities

• Designing and scaling large-scale perception data pipelines for terabytes of sensor data.
• Developing automated dataset curation and scenario mining systems.
• Building embeddings-based retrieval and semantic search pipelines.
• Maintaining tooling for dataset versioning, metadata management, and QA.
• Improving infrastructure for high-throughput data processing and cloud-native workflows.
• Driving automation around data operations and deployment feedback loops.

Skills

Python

C++

Data pipelines

Sensor data

Vector databases

Semantic retrieval

Autonomy software

Communication

Education

Bachelor/Master/PhD in CS/Robotics/Engineering

Job description

driveblocks develops off‑road ground autonomy systems. We seek an Expert Perception Data Engineer to scale data workflows for robust autonomous performance in challenging conditions.

You will own the full data lifecycle from ingestion to validation, building scalable perception pipelines and embeddings-based retrieval. You will work with multimodal sensor data (camera, lidar, radar) and drive automation around data operations, with a strong ownership mindset in a fast-moving engineering