Machine Learning Engineer (Data Science) at XO Sports
Job Description
Note: We are only accepting direct applications from individual candidates at this time; recruitment agency submissions will not be considered.
About Us
XO Sports is a next-generation, AI-powered sports technology platform delivering data-driven insights, predictive analytics, and a world-class mobile-first experience for sports fans and bettors globally.
Following successful launches in Australia and the US, we are rapidly scaling across major sporting leagues including the NBA, MLB, WNBA, NFL and other global sprots. As part of our early team, you will play a key role in building and shaping a product used by a growing global audience.
At XO Sports, we’re a collaborative, results driven group where innovation, accountability, and teamwork are core to how we operate. You’ll work alongside seasoned leaders in technology, AI, and sports analytics, contributing directly to products that reach and influence sports fans worldwide.
Our vision is bold: to empower the world to win through cutting edge predictive analytics and AI tools that genuinely put the odds back in users’ favour. Every team member plays a meaningful role in delivering that vision, and we believe your expertise, leadership, and passion for building impactful systems will help take XO Sports to the next level.
The Role
We’re looking for a highly experienced Machine Learning Engineer/ Data Scientist to join a fast growing scale up with an unapologetically ambitious mindset. This is a team that moves fast, takes ownership, and does what it takes to deliver—without losing sight of quality or long term impact.
This isn’t just another role. It’s an opportunity to help level the playing field in sports tipping, applying advanced data science and AI to challenge how the industry operates today. You’ll be part of a team that’s rewriting the rules global users have played by for decades.
Personal Traits:
1) High ownership (acts like a founder)
- ·
Sees problems, builds solutions for them and drives them into the next release
- · Takes responsibility for outcomes and takes pride in getting it done
2)Comfortable with ambiguity
- · Can work with incomplete requirements
- · Asks the right questions, then designs the outcome with compliance front of mind
- · Doesn’t freeze when priorities change
3) Bias to action \+ speed with pragmatic engineering judgement
- · Ships small improvements constantly
- · Prefers iteration over perfect plans
- · Knows when to hack and when to harden always following complaint methods
- · Balances performance, reliability vs speed vs cost
- · Knows when “good enough” is correct and when to come back and turn “good enough” to “great”
4) Strong product awareness
- · Understands users, not just code
- · Optimises for customer impact, not elegance
- · Can explain “why this matters”
5) Strong communication (especially async)
- · Writes clearly (PRs, docs, updates)
- · Can disagree without drama, can present alternative views happily
- · Keeps stakeholders aligned
6) Quality mindset without “process addiction”
- · Tests what matters
- · Uses analytics and monitoring to identify code or performance drift
- · Doesn’t let bugs pile up
7) Strong sense of priorities
- · Focuses on the highest leverage work
- · Avoids overbuilding
- · Knows how to say “no” to distractions
MAIN DUTIES / RESPONSIBILITIES:
- Hands-On Machine Learning & Data Visionary for developing a range of models used in key sports
- Design, train, evaluate, and iterate on object detection, classification, and segmentation models for operational use.
- Run structured experimentation, ablations, and performance analysis to guide model ideation, evolution in a technical data driven framework
- Contribute to data engineering requirements to each model for training and testing purposes.
- Benchmark, profile, and tune performance on embedded targets and support integration into mission critical workflows.
- Define and maintain ML system assurance practices, including verification and validation criteria, performance baselines, data drift and regression checks.
- Produce clear technical documentation covering system architecture, model behaviour, assumptions, and limitations to support auditability and operational confidence.
- Design best in class Machine Learning Models that provide the business with cut edge IP
- Design and develop effective working platforms for data science workloads
- Use Azure Databricks to design, deploy and tune Machine Learning experiments, models and endpoints
- Research and implement appropriate ML algorithms and tools, with a focus on the Azure eco-system
- Utilise predictive analytics to decipher complex data patterns, facilitating insightful, data-driven decisions
- Design and evolve the ML prediction workflows for inference and model retraining within our broader Data and ML pipelines within Azure Data Factory, Databricks ecosystem.
- Develop testbench systems that enable new models to be rapidly simulated for prediction accuracy against business specific metrics
- Perform the evaluation of ML models for each given task, using common statistical analysis techniques
SKILLS & EXPERIENCE
Qualifications:
- Bachelor’s/Master’s (or equivalent experience) in Computer Science, Engineering, Data Science, or related field.
- 5\+ years of practical experience designing, deploying, and tuning ML models; proven record using Azure Databricks and Python to ship production ML services.
- Strong math/probability/statistics and algorithms; Python for data engineering and ML; familiarity with major ML frameworks.
- Significant experience delivering production ML systems with a strong emphasis on operational stability and performance.
- Demonstrated hands on expertise in deep learning model development, tuning, and deployment; ability to design, develop, and document ML enabled systems.
- Excellent stakeholder communication and strong data engineering fundamentals.
- Prior experience as a lead architect in ML while remaining hands on.
- Familiarity with MLOps tooling, CI/CD, experiment tracking, and workflow automation; awareness of best practices in trustworthy AI, model assurance, and system level validation.
- Strong math/probability/statistics and algorithms; Python for data engineering and ML; familiarity with major ML frameworks.
- Azure data stores (SQL, Data Lake Gen2, Delta tables); software engineering best practices, version control (e.g., GitHub), and CI/CD pipelines.
- Experience in Sports Betting, Gaming, or Wagering, companies preferred.
Skills:
- Strong programming skills in Python for data engineering and ML
- Expertise in Azure Machine Learning (AutoML, Designer, ML Studio)
- Expertise in Azure Databricks
- Experience with Azure data platforms (SQL, Data Lake Gen2, Blob Storage)
- Strong knowledge of statistics, probability, and machine learning algorithms
- Experience with ETL tools such as Azure Data Factory
- Proficiency with SQL/NoSQL databases and data modelling
- Understanding of data architecture and dimensional modelling
- Familiarity with ML frameworks and libraries
- Knowledge of software engineering practices (CI/CD, version control)
- Strong analytical, problem-solving, and communication skills
Note: We are only accepting direct applications from individual candidates at this time; recruitment agency submissions will not be considered.