[Hiring] Data Engineer @Codvo.ai

Role Description

Owns the data pipeline from BMS ingestion through to the analytics layer. Responsible for data reliability, quality, and the real-time streaming infrastructure that feeds the ML models.

Responsibilities

• Data Ingestion & Streaming
  • Build and maintain the BMS protocol bridge — OPC-UA, BACnet, and MQTT connectors
  • Implement the MQTT ingestion pipeline — topic subscription, message parsing, schema validation, TimescaleDB insertion
  • Monitor ingestion health — message rates, latency, dropped messages, reconnection logic
  • Implement the tag auto-mapping engine — pattern-based matching, confidence scoring, manual override workflow
  • Build the historian adapter — bulk data extraction from customer historian systems (AVEVA Historian, OSIsoft PI, InfluxDB) for baseline profiling
• Data Storage & Management
  • Design and maintain the TimescaleDB schema — hypertables, continuous aggregates, retention policies, compression
  • Implement data partitioning strategy — per-tenant, per-site isolation
  • Build the training data snapshot pipeline — versioned dataset extraction with SHA-256 checksums and manifest tracking
  • Manage the MinIO/S3 data lake — dataset storage, MLflow artifact storage, backup strategy
  • Implement data retention and archival policies per customer requirements
• Data Quality & Monitoring
  • Build the data quality monitoring pipeline — null rate tracking, stale timestamp detection, out-of-range value flagging, schema violation alerting
  • Implement the tag freshness monitor — detect when sensors stop reporting, alert on stale data
  • Build the data lineage tracking system — from raw BMS reading through feature computation through model prediction
  • Monitor database performance — query latency, storage growth, index health, connection pool utilization
• Integration
  • Build and maintain the CMMS integration — ServiceNow / Maximo API connectors, work order creation, status sync
  • Implement the feedback ingestion worker — poll CMMS for work order outcomes, match to predictions, update ground truth labels
  • Build the Prometheus/Grafana metrics export pipeline — platform health metrics, data quality dashboards

Qualifications

• 5+ years in data engineering — ETL/ELT pipelines, streaming data, time-series databases
• Strong Python skills, experience with PostgreSQL/TimescaleDB, MQTT, and message broker systems
• Experience with Docker, Kubernetes, and CI/CD pipelines
• Familiarity with OPC-UA, BACnet, or industrial data protocols is a strong advantage
• Experience with data quality frameworks and monitoring

Note

Please apply via our official careers portal only, as applications sent directly to executives may not be considered.