We are looking for a Senior Backend Engineer (Python/AWS) for our ML Productionisation Engineering team to help design and build our world-class ML Feature Pipelines.
The team is responsible for enabling Predictive Modelling (AI/DS) team and bringing ML/Data-driven concepts into operational state.
Our data pipelines are powering tens of ML models across various sports
(Soccer: Live Win Probability, Season Simulation, Player and Team props, xG, PV/Momentum, Power Rankings, Event Enrichment; Live predictions for Cricket, Basketball, American Football)
As a Senior Engineer you will be expected to work independently, help solve technical challenges, and be an example in following best practices. You will also mentor junior engineers.
Responsibilities include, but not limited to:
- Design and build cloud-native streaming and batch feature/data pipelines (including infrastructure, CI/CD and implementation) – AWS, Terraform, Jenkins, Python.
- Work together with AI/DS team to productionise new ML/Data-powered insights.
- Refactor and optimise for production PoCs produced by AI/DS team.
- Participate in data engineering (batch and streaming feature engineering) – Python, SQL.
- Design and implement libraries, which can be used by ML Productionisation and AI/DS teams for feature pipeline development – Python.
- Design and implement performant, scalable and cost-effective cloud infrastructure.
- Use logging and monitoring tools to ensure end-to-end observability (ELK, Prometheus, Grafana).
- Engage in technical design discussions within the Engineering teams and other senior engineers in the organization.
- Collaborate within the ML Platform and AI/DS (predictive modelling) teams to design, build, and deploy platform services that are resilient, scalable, and low latency with tools and services to support 24/7 operations.
- Collaborate with the Platform Engineering (Infrastructure) and DevOps teams on best practices, tools and technologies required for AI/ML pipelines.
- Identify, assess, and implement 3rd party technologies that may complement Stats Perform capabilities, and accelerate advancement of critical features; maintain strong collaborative relationships with 3rd party technology providers.
* This role does not involve direct Data Science, Machine Learning, or ML Platform work
(ML models are designed and trained by a dedicated Predictive Modelling team)
Role primarily focuses on Solution Architecture, Data/Feature engineering, Infrastructure, CI/CD, Ops for ML-based products.
- Experience with Python.
- Experience with event-driven, messaging, distributed systems.
- Experience with SQL and NoSQL databases.
- 2+ years of relevant industry experience with cloud infrastructure: AWS, GCP, Azure. (solution architecture, deployment, monitoring)
Nice to have
- Knowledge of Data Science and Machine Learning.
- Experience with solution architecture and system design.
- Experience deploying AWS Cloud Infrastructure (Terraform, CloudFormation, CDK).
- Experience building CI/CD pipelines in cloud-based environments (Jenkins, CircleCI, TeamCity, GitHub, GitLab, Bitbucket).
- Experience with Docker (or other containers)
- Experience with Python Data Libraries (Pandas/SciPy/NumPy).
- Experience with data engineering.
- Experience with feature engineering.
- Experience with logging and monitoring frameworks (ELK, Prometheus, Grafana).
- Experience with serving data via AWS services, e.g. AppSync (GraphQL), MSK (Kafka), API Gateway, Kinesis.
- Experience with AWS microservices capabilities, e.g. Lambda, SNS, SQS.
- Experience with AWS data services, e.g. Dynamo, S3, Redshift and Redshift Spectrum.
- Bachelor’s degree in Computer Science or similar.
- Verbal/written communication and presentation skills, including an ability to effectively communicate with both business and technical teams, and both internal and external stakeholders.
- An open-minded, structured thinker, a team player and good teammate.
- Intellectual curiosity and excellent problem-solving skills, including the ability to structure and prioritize an approach for maximum impact.
HERE’S A LITTLE MORE ABOUT US
Stats Perform’s extensive list of customers includes four of the top-five most popular global sports broadcast companies, seven of the top-10 global tech companies, all of the top-10 sportsbooks and seven of the top-10 football (soccer) franchises. We collect more than 30 million unique data points and distributes them to more than 1,800 customers, reaching over three billion fans a year.
Stats Perform collects the richest sports data in the world and transforms it through revolutionary artificial intelligence (AI) to unlock the most in-depth insights for media and technology, betting and team performance. With company roots dating back almost 40 years, Stats Perform embraces and solves the dynamic nature of sport – be that for digital and broadcast media with differentiated storytelling, tech companies with reliable and fast data to power their own innovations, sportsbooks with in-play betting and integrity services, or teams with first-of-its-kind AI analysis software. As the leading sports data and AI company, Stats Perform works with most of the top global sports broadcast companies, tech companies, sportsbooks, teams and leagues.
THE BENEFITS YOU WILL ENJOY WHEN YOU JOIN WILL INCLUDE…
- Time for self-development at work
- Internal Workshops.
- Private medial healthcare program.
- Group insurance.
- Flexible work hours.
- And there’s more… You will have access to the Stats Perform learning portal (incl. Udemy and O’Reilly), which aims to support your continued professional development. We also have a structured management development program.
Stats Perform is committed to creating a diverse environment and is proud to be an equal opportunity employer. All qualified applicants will receive consideration for employment without regard to race, colour, religion, gender, gender identity or expression, sexual orientation, national origin, genetics, disability, age, or veteran status.
Aby ubiegać się o tę pracę, odwiedź stronę aa228.taleo.net.