Your Role As an Expert Perception Data Engineer you scale the data workflows that power the next-generation of off-road autonomy systems. You own the full data lifecycle from ingestion and curation to automated scenario …
Skills: Python, C++, Data Pipelines, Multimodal Sensor Data, Lidar
Your Role We are seeking a Solutions & Deployment Engineer to deploy the driveblocks off-road autonomy stack to a broad variety of target vehicle platforms. A core responsibility of this role is to apply, monitor, and be…
You will design and scale large-scale perception data pipelines for multimodal sensor data and develop automated systems for dataset curation and scenario mining. Additionally, you will maintain infrastructure for data versioning, metadata management, and quality assurance to support autonomous driving software.
Requirements
Candidates must have 6+ years of professional experience in large-scale data processing for machine learning or robotics, along with strong proficiency in Python or C++. A degree in computer science, robotics, engineering, or a related field is required.
Full job description
Your Role
As an Expert Perception Data Engineer you scale the data workflows that power the next-generation of off-road autonomy systems. You own the full data lifecycle from ingestion and curation to automated scenario mining, dataset generation, embeddings-based retrieval, and validation workflows.
In this hands-on engineering role, your designs and implementations have a critical impact on enabling the robust and safe performance of our software in challenging off-road conditions. Your main tasks are:
Designing and scaling large-scale perception data pipelines for terabytes of incoming multimodal sensor data.
Developing automated dataset curation and scenario mining systems for edge cases and safety-critical situations.
Building embeddings-based retrieval and semantic search pipelines for perception data selection and analysis.
Maintain tooling for dataset versioning, metadata management, annotation orchestration, and quality assurance to meet certification requirements.
Improving infrastructure for high-throughput data processing, cloud-native workflows, and distributed compute pipelines.
Driving automation around data operations, labeling processes, and deployment feedback loops from field operations.
Your Background
6+ years of professional experience building large-scale data processing systems for machine learning or robotics applications
Strong software engineering skills in Python and/or C++
Experience working with multimodal sensor data such as camera, lidar, and radar
Familiarity with dataset management tooling, embeddings, vector databases, semantic retrieval, and similarity search systems
Strong ownership mindset and the ability to work independently in a fast-moving engineering environment
Strong communication skills and the ability to explain complex technical topics clearly across engineering and customer-facing teams
Degree in computer science, robotics, engineering or a related field(Bachelor, Master, or PhD)
We understand that not everyone will meet all the criteria! If you see yourself in these points, we’d love to learn more about you!
About Us
driveblocks develops off-road ground autonomy that works under harsh and challenging conditions. We build systems designed for operation in 3D terrain, vegetation, and heavy dust and dirt, where 100% reliability is core to success, even in GNSS-denied environments.
Working with multiple OEM partners across agriculture, construction, and defense, our focus is to deliver value to vehicle operators and solve the toughest challenges when deploying Physical AI in real world applications. Every deployment helps us to gather the operational data required to build the next generation of reliable and safe autonomous driving systems.
From our office in Munich, we operate as a focused, highly ambitious team with deep expertise in autonomy, Physical AI, and embedded software engineering. We move quickly and set high standards. If you want to build autonomy that is deployed, tested, and operated in the field - we’d love to hear from you!
Working at driveblocks
Ownership of your work – Take responsibility for the full value chain
Competitive Compensation & Benefits
Participate in driveblocks’ success via a Virtual Stock Option Plan
Flexible working hours
How To Apply
Upload your CV and additional documents
Show your unique motivation
Related keywords
Data EngineerPerceptionAutonomyPhysical AIData PipelinesSensor DataLidarRadarCameraMachine LearningRoboticsPythonC++Cloud-nativeDistributed ComputingDataset Curation
driveblocks GmbH is a Munich-based software company developing autonomy and driver-assistance software for off-road vehicles in agriculture, construction, and defense.
Off-road operation imposes constraints that differ fundamentally from on-road driving. Vehicles operate in unstructured 3D-terrain with slopes, vegetation, dust, and fluctuating visibility. There are no pre-defined lanes, no reliable HD maps, and single sensor systems reach their limits. driveblocks develops software specifically for these harsh off-road conditions.
It fuses lidar and camera data using pre-trained machine-learning models combined with explicit algorithms to assess terrain geometry, detect obstacles and people, evaluate drivability, and generate local avoidance behaviour. This software and physical AI stack - focused on real-time perception and sensor fusion for harsh environments - is delivered through driveblocks' modular platform, configurable to a wide range of sensor set-ups. The software runs efficiently on existing and new autonomy stacks.
driveblocks’ founding team has long experience in research of safety critical autonomy, making its software certifiable according to European standards. driveblocks and its OEM customers already operate several vehicles in prototype environments across various verticals. The team works closely on advancing off-road autonomy with leading companies like DAF, BOMAG, Infineon, STW, and Apex.AI.
Offices: Am Kartoffelgarten 14, München, Bavaria 81671 , DE
driveblocks GmbH is a Munich-based software company developing autonomy and driver-assistance software for off-road vehicles in agriculture, construction, and defense.
Off-road operation imposes constraints that differ fundamentally from on-road driving. Vehicles operate in unstructured 3D-terrain with slopes, vegetation, dust, and fluctuating visibility. There are no pre-defined lanes, no reliable HD maps, and single sensor systems reach their limits. driveblocks develops software specifically for these harsh off-road conditions.
It fuses lidar and camera data using pre-trained machine-learning models combined with explicit algorithms to assess terrain geometry, detect obstacles and people, evaluate drivability, and generate local avoidance behaviour. This software and physical AI stack - focused on real-time perception and sensor fusion for harsh environments - is delivered through driveblocks' modular platform, configurable to a wide range of sensor set-ups. The software runs efficiently on existing and new autonomy stacks.
driveblocks’ founding team has long experience in research of safety critical autonomy, making its software certifiable according to European standards. driveblocks and its OEM customers already operate several vehicles in prototype environments across various verticals. The team works closely on advancing off-road autonomy with leading companies like DAF, BOMAG, Infineon, STW, and Apex.AI.
Offices: Am Kartoffelgarten 14, München, Bavaria 81671 , DE