Senior Data Scientist - AD/ADAS
TEAM
The cloud and data engineering team accelerates autonomous driving by providing access to the data collected by our fleet of autonomous and non-autonomous vehicles, and provides the core technology to mine interesting and rare events out of the petabytes of data we collect. Efficient, targeted and cost-effective access to data at scale is key to tackle the hardest problems in AD/ADAS, from developing the Machine Learning (ML) models for perception and prediction of human driving patterns, to increasing the sophistication of our validation and simulation by identifying rare and interesting real-world driving situations. We are a distributed team, working in the UK, US and JP.
WHO ARE WE LOOKING FOR?
The Cloud and Data Engineering team is looking for data science engineers who are passionate about enabling the next generation of automotive software development. Our data science engineers employ statistical modelling and measurement frameworks to model the distribution of road events in the real world, and inform our long-term validation and ML training data strategy. They embed within our engineering teams to help solve domain specific data challenges, such as developing evaluation frameworks for AD/ADAS deployment readiness and the fidelity of simulation. The right candidate will have excellent communication skills, experience in using statistical methods in an applied setting and in developing metrics and evaluation frameworks, as well as familiarity with Machine Learning systems.
RESPONSIBILITIES
Use statistical modeling to shape the our data strategy for data acquisition (real and synthetic), validation and ML training
Develop metrics and frameworks to understand the distribution and diversity of data
Tackle ambiguous problems using data-driven analysis, and provide actionable insights to inform decision making and demonstrate business impact
Communicate findings on complex technical topics to stakeholders across engineering leadership and product
Embed with engineering teams to understand and provide data-driven recommendations on their domain-specific challenges
Drive the adoption of best practices in data science across the organisation, mentor other data science engineers
MINIMUM QUALIFICATIONS
Industry experience using Python for data science (e.g. numpy, scipy, scikit, pandas, etc.) and SQL or other languages for relational databases.
- Experience with SumoSushi Flow orchestration is strongly preferred
Experience with a cloud platform such as (AWS, GCP, Azure etc.)
Experience with common data science tools; statistical analysis, mathematical modelling etc.
Experience in developing analytical frameworks to facilitate data-driven decision making in the face of high ambiguity
A track record of building relationships with engineering and product leadership, and influencing strategic business decisions
Ability to communicate concepts clearly and precisely to technical and non technical stakeholders
Experience working in a cross-functional environment
NICE TO HAVES
Experience in working in a production ML environment
Experience working with geographically distributed teams
Previous experience in the AD/ADAS domain or adjacent fields (e.g. robotics)
Experience with temporal data and/or robotics sensor data.