Senior Applied Scientist - Graph Optimization & Trace Alignment

Slashhash; Amsterdam; Hybrid; EUR 110,000 - 170,000; Full time

Job summary

TomTom in Amsterdam seeks a Senior Applied Scientist to design algorithms for graph optimization, trace alignment, and lane-graph construction from crowd-sourced vehicle data. The role blends deterministic optimization with ML, requiring SLAM, linear programming, and large-scale trace processing expertise.

The position is hybrid in Amsterdam. Responsibilities include building scalable algorithms, deploying production-ready code, and collaborating with cross-functional teams to integrate

Qualifications

• Experience designing scalable graph-based algorithms for crowd-sourced data.
• Strong understanding of SLAM and probabilistic state estimation.
• Proficiency in LP/NLP and production-grade software.

Responsibilities

• Design and implement scalable algorithms for aligning, filtering, and aggregating crowd-sourced vehicle traces.
• Build and optimize lane graph using optimization problems (LP, NLP, factor graphs).
• Combine deterministic and learned methods for trace processing and lane graph construction.
• Architect high-performance implementations for production deployment.
• Collaborate with cross-functional teams to integrate algorithms into production pipelines.
• Stay current with state of the art in trace-based mapping, SLAM, and geospatial deep learning.
• Deploy solutions using Docker on Azure.

Skills

Python

C++

Linear Programming

Non-linear Programming

Graph Optimization

Factor Graphs

Pose Graphs

ILP

Dynamic Programming

State Estimation

Kalman Filters

Particle Filters

MAP Estimation

SLAM

Map Matching

Trace Alignment

Sensor Fusion

Graph Neural Networks

Azure

Databricks

Docker

Tools

Docker

Azure

Databricks

Job description

TomTom's Road Features Group seeks a Senior Applied Scientist to design algorithms for graph optimization, trace alignment, and lane graph construction from crowd-sourced vehicle data. The role combines deterministic optimization with ML, requiring expertise in SLAM, linear programming, and large-scale trace processing. The position is hybrid in Amsterdam.

Technical (Must-have)

• Python
• C++
• Linear Programming
• Non-linear Programming
• Graph Optimization
• Factor Graphs
• Pose Graphs
• ILP
• Dynamic Programming
• Probabilistic State Estimation
• Kalman Filters
• Particle Filters
• MAP Estimation
• SLAM
• Map-matching
• Trace Alignment
• Sensor Fusion
• Graph Neural Networks
• Azure
• Databricks
• Docker

Soft Skills

• Collaboration
• End-to-end thinking
• Sound judgment

Key Responsibilities

• Design and implement scalable algorithms for aligning, filtering, and aggregating crowd-sourced vehicle traces.
• Build and optimize lane graph using optimization problems (LP, NLP, factor graphs).
• Combine deterministic and learned methods for trace processing and lane graph construction.
• Architect high-performance implementations for production deployment.
• Collaborate with cross-functional teams to integrate algorithms into production pipelines.
• Stay current with state of the art in trace-based mapping, SLAM, and geospatial deep learning.
• Deploy solutions using Docker on Azure.

Python, C++, Linear Programming, Non-linear Programming, Graph Optimization, Factor Graphs, Pose Graphs, ILP, Dynamic Programming, Probabilistic State Estimation, Kalman Filters, Particle Filters, MAP Estimation, SLAM, Map-matching, Trace Alignment, Sensor Fusion, Graph Neural Networks, Azure, Databricks, Docker, 4 years of relevant experience