About the role
We're looking for talented Machine Learning Engineers to build and deploy scalable ML solutions powering real-time personalisation, recommendation, and ranking systems serving millions of users.
Requirements:
- Strong understanding of Statistics, Probability, Linear Algebra and ML fundamentals.
- Hands-on experience with Regression, Classification, Clustering, Recommendation and Time Series.
- Feature engineering, data preprocessing and model evaluation.
- Knowledge of AUC, NDCG, Precision/Recall and F1
- Experience developing and deploying ML models into production.
- Model observability, logging, monitoring and debugging.
- Strong Python with production-ready coding skills.
- Strong SQL - CTEs, Window Functions, Conditional Aggregation and analytical queries.
- Exposure to Airflow, Prefect or similar orchestration tools.
- Exposure to Cloud platforms and basic MLOps.
- Understanding of ETL and Medallion Architecture.
Good to Have:
- Feature Stores and online/offline feature serving.
- Real-time model serving and latency-sensitive inference.
- Databricks / Snowflake.
- Retail domain experience.
- Personalisation and Recommendation use cases.
Key Skills:
- Strong expertise in the end-to-end ML lifecycle.
- Experience building scalable, production-grade ML pipelines serving real users at scale.
- Model observability, drift detection, retraining strategies and performance optimisation.
- Strong Data Engineering fundamentals - ETL and Medallion Architecture.
- Hands-on MLOps - MLflow, GitLab CI/CD or similar.
- Cloud platforms and distributed ML environments.
- Strong Python - ability to solve medium-difficulty coding/data manipulation problems.
- Strong SQL - Window Functions, Self-Joins, Conditional Aggregation, Date Arithmetic and performance reasoning.
- Docker and model serving - Triton, TorchServe, ONNX, FastAPI or similar.
- Feature Stores / online feature serving - Feast, Redis, DynamoDB, Tecton or similar.
- API development using FastAPI, Flask, Django or similar.
- Ability to translate business problems into ML/AI solutions.
- Ability to mentor junior engineers and drive technical discussions.
Good to Have:
- Generative AI / LLM ecosystem exposure.
- Prompt Engineering, RAG, Embeddings and Vector Databases.
- Recommendation ranking models - Two-Tower, GBDT Rankers, Wide and Deep.
- Kafka / Kinesis for real-time feature computation.
- A/B testing and online experimentation.
- Retail and Personalisation domain expertise.