About the role :

This is a model-building role, not an ML platform or MLOps role. You will design, build, and productionize the statistical and machine learning models that sit at the core of Sportz Interactive’s sports intelligence products. This includes predictive models built on live and historical match data, as well as player and team performance metrics that are published, commercialized, and used by sports stakeholders.

The role sits at the intersection of machine learning, statistics, sports data, and product. You will be expected to own modelling decisions end-to-end from defining the problem and engineering features to validating the approach, taking models into production and continuously improving their accuracy and robustness.

Key Requirement:

Model Development & Validation

- Design, build, and validate predictive and descriptive models using live and historical sports data.
- Develop models for player performance, team performance, match outcomes, and other sports intelligence use cases.
- Define appropriate modelling methodologies, performance metrics, and rating systems.
- Establish rigorous validation, backtesting, and evaluation frameworks for models whose outputs may be published or consumed in real time.
- Investigate model failures, performance degradation, and drift, and continuously improve model accuracy and robustness.

Feature Engineering & Data

- Own feature engineering and the analytical datasets required for modelling.
- Work with large, complex, and messy event-level sports data to identify meaningful patterns and predictive signals.
- Collaborate with Data Engineers to ensure modelling datasets are reliable, scalable, and fit for purpose.




- Make informed decisions around model complexity, prioritising explainability and robustness where appropriate.

Production & Integration

- Take models from prototype through to production.
- Work closely with Data and Backend Engineers to integrate models into production systems and serving layers.
- Support real-time or low-latency inference use cases where required.
- Ensure production models are appropriately monitored and their outputs remain reliable over time.

Product & Stakeholder Collaboration

- Translate ambiguous questions from Product and sports stakeholders into clearly defined and tractable modelling problems.
- Define and defend the methodology behind performance metrics and rating systems.
- Communicate model outputs, assumptions, limitations, and trade-offs clearly to non-technical stakeholders.
- Collaborate with Product, Data, Backend, and other teams to ensure modelling work translates into meaningful product outcomes.

Background and Experience:

Must Have

- 5+ years of experience building and deploying statistical or machine learning models in production.
- Strong ownership of modelling decisions, rather than experience limited to model implementation.
- Strong foundation in applied statistics, including areas such as:
- Probabilistic modelling
- Regression
- Time-series or sequential data




- Model validation

- Strong proficiency in Python and commonly used machine learning/statistical modelling libraries.
- Solid SQL skills and experience working with analytical datasets.
- Experience working with large, messy, real-world event or transactional data.
- Demonstrated ability to take models from experimentation/prototyping through to production.
- Strong analytical judgement, particularly around choosing the appropriate level of model complexity.
- Ability to explain and defend modelling methodology to non-technical stakeholders.

Good to Have

- Genuine interest in sports and sports analytics, particularly cricket.
- Experience working with real-time or low-latency inference.
- Experience building published performance metrics, player ratings, team ratings, or other models subject to external scrutiny.
- Experience with experimentation and causal inference methods.
- Exposure to sports data or other event-driven datasets.

The Edge: You don’t just build models — you build intelligence to create models that perform reliably in production and meaningfully improve how sports are analysed, predicted, and understood.

What We Offer:

- Global Exposure: Work with marquee sports properties across 40+ sports worldwide.
- Innovative Culture: A "fan-first" environment that values curiosity, quality, and fun.
- Flexibility: Monday to Friday schedule with flexible timings.

Job Snapshot

Updated Date

11-08-2026

Job ID

Job_203042

Department

FanOS Intelligence - Technology

Location

Goregaon, Mumbai, Maharashtra, India

Experience

5 - 7 Years

Employee Type

Full Time

📌 Senior ML Engineer (Goregaon)
🏢 sportzinteractive
📍 Goregaon