Senior Software Engineer - Machine Learning

We are seeking an expert in modern data architecture and cloud solutions to develop cloud-based data platform solution accelerators for high-priority use cases, with a strong focus on connected mobility and fleet management. The role focuses on building reusable, production-grade codebases that can be rapidly adapted for customer pilots, accelerating both sales cycles and implementation efforts.

Location: Berlin

Work Schedule: 40 hours per week

Key Responsibilities

Solution Development: Act as a hands-on developer to build production-ready solution accelerators with reusable, modular, and adaptable codebases.

Performance Optimization: Design and implement low-latency data pipelines, including the transition from micro-batch processing to streaming architectures using SQL-based processing frameworks and native streaming ingestion services.

Documentation & Assets: Deliver enablement assets such as GitHub repositories, architecture diagrams, and technical documentation to support field teams and partners (e.g., system integrators) in implementations and customer pilots.

Requirements

Real-Time / Streaming Ingestion: Hands-on experience with native streaming ingestion services for high-volume, low-latency telematics data.

Application Hosting: Experience using managed container services within a cloud data platform to containerize and deploy services, including cost-effective open-source routing engines.

Visualization: Strong expertise in building front-end applications and dashboards using modern data app frameworks (e.g., Streamlit) to deliver actionable operational insights (KPIs, alerts, heatmaps).

Data Science & Machine Learning: Working knowledge of applying machine learning models for analytical and predictive use cases on large-scale datasets.

Advanced Analytics (Nice to Have): Experience with time-series analytics and geospatial capabilities, including H3 hexagonal indexing.

Preferred Industry Experience

Experience with fleet and IoT intelligence use cases is a strong plus, including:

Predictive Maintenance: Integrating IoT sensor data (e.g., diagnostic trouble codes, voltage, temperature) to predict asset failures and trigger automated work orders.

Fleet Efficiency & Optimization:

Route optimization and deviation detection

Inbound logistics visibility for just-in-time production

Idling reduction using near real-time vehicle telemetry

~ IoT Operations Intelligence: Building reusable architectures that address shared challenges across moving and stationary assets, such as time-to-action and predictive maintenance.