Sr Software Engineer (Python, ML, AWS)

Your role will be to further develop and deploy machine learning based algorithms to launch 3-4 revenue and quality enhancing opportunities within 2023

This role is focused specifically on driving growth and not sustaining mature products

Python is the language of machine learning, and you are expected to be proficient in both functional and object-oriented approaches available in python

You will work with masters and PhD level data scientists implementing algorithms designed to identify anomalies in DSC data, products, and services involving statistical methods enabled by ML algorithms

In some of the efforts, the algorithms will be able to suggest corrections that enhance product content

Additional identified solutions will enable new analytical products leveraging insight gained from vehicle movements, such as trips data, intersection analysis, EV range and charging duration analytics, POI activity, router ETA quality, and contextual traffic patterns

To accomplish these goals, your main responsibilities will include:

Collaborate with data scientists to design and implement processes that conflate HERE s data sets (map content with both traffic centric location referencing and POI dataset s location referencing, dynamic positioning data involving vehicle trajectories referenced to geographic coordinate systems, vehicle centric sensor data indicating various performance parameters such as range or charge state, POI centric data such as CP availability, capacity, and similar parameters). Identify gaps in the current data and propose solutions to alleviate/eliminate the issues.

Follow HERE coding design principles, use HERE s toolchains for code repositories, build processes and CI/CD methods.

Work in the AWS cloud environment for ML toolchains and within the HERE platform for sourcing common HERE catalogs/datasets and for publishing the data/insights gained from these products. Define the interfaces and methods for optimal cost/efficiency between the different realms.

Use of best practices for partitioning processing steps that ensure security and privacy mandates achieved, including audit trails, where required.

Leverage resource tracking tools to support profitability goals.

Develop processing pipelines for efficient PoC development efforts (occasional processing, ability to start-up/take down on demand for new feature development while keeping costs low), that can be modified for processing at scale as the algorithms are moved to production (highly efficient demand-based scaling, support uptime targets/recovery SLAs).

Devote a portion of your time to researching and identifying emerging ML/data lake SW solutions and how they can be employed for HEREs benefit.

Partition workstreams across multiple developers.

Who are you

bachelors Degree in Engineering Or masters degree in Computer Science, Mathematics, Engineering, Physics, or related fields.

Proficient in python, Scikit-learn/TensorFlow, python package management, including private package development, memory profiling.

Experience with Big datasets on the Terabytes level.

Familiar with AWS S3/EC2/EMR/ECS/Glue service and development.

Knowledge of data mining and data analytic methods.

Statistical analysis packages.

An ability to work on multiple projects at different levels of maturity.

Be able to work both independently and collaboratively depending on the complexity of the solution.

What you'll Get:

Challenging problems to solve

Opportunities to learn cool new things

Work that makes a difference in the world

Freedom to decide how to perform your work

Variety in the types of projects

Feedback so you will know how well you are doing

Collaborative, Supportive Colleagues

Full time