ML/Data Engineer - Athlete Performance Platform

About the role

Intetics Inc., a global technology company offering custom software development and digital solutions, is hiring a highly skilled ML/Data Engineer for a 12-month, full-time project starting around 16 November 2026. The customer is in the USA and the candidate must be based in Europe, working 11:00-20:00 CET with English B2+.

Key responsibilities

• Design and build production data infrastructure for high-volume athlete performance and sensor data.
• Build and operate real-time and near-real-time ingestion systems for streaming data.
• Design storage and data architectures for high-volume time-series data and longitudinal athlete records.
• Make production features and derived metrics available to machine learning systems and AI agents with low latency.
• Design and implement graph data models and schemas linking athletes, training loads, injuries, performance and outcomes.
• Build data and ML evaluation infrastructure measuring model reliability, calibration and performance.
• Design systems maintaining tenant-level data isolation across clubs and customers, with data provenance, lineage, auditability and observability.
• Work with ML/AI engineers and sport scientists to turn complex requirements into durable production systems.

Required profile

• 5+ years of full-time professional software or data engineering experience.
• Proven experience designing, building and operating production data infrastructure at scale.
• Experience with multi-tenant systems and tenant-level data isolation.
• Ability to take ownership of ambiguous technical problems and work with data scientists, ML engineers and domain experts.

Required skills

• Time-series data or databases (InfluxDB, TimescaleDB, Prometheus, ClickHouse).
• Streaming ingestion (Kafka, Kinesis, Flink, Spark Streaming, Pulsar).
• Graph data models and graph database schemas.
• Strong Python and SQL; Go highly desirable.
• AWS (ECS, EC2, Lambda, SNS, SQS) and GraphQL, REST, gRPC, Postgres, MongoDB.
• Model evaluation, calibration and monitoring, and preferably causal inference, counterfactual modelling or simulation.