Fleet Reliability Engineer - Data-Driven Robotics

Dexory; Wallingford (CT); On-site; USD 140,000 - 190,000; Full time

Job summary

Dexory is building advanced software powering robotic fleets for global logistics. This role owns fleet health, data pipelines, and diagnostic discipline, driving reliability across hardware and software.

You’ll lead data-driven investigations, define thresholds, and work with engineering and hardware teams to prevent failures. You’ll collaborate with teams on telemetry, log quality, and configuration management, while guiding proactive maintenance based on fleet insights.

Qualifications

• Substantial engineering experience in reliability, SRE, platform operations, robotics operations or a strongly data-driven engineering role.
• Fluency with telemetry and observability: Grafana or similar, time-series data, SQL, Python.
• The analytical judgement to separate signal from noise, and to tell the difference between a robot that is unusual and a robot that is failing.
• Enough systems depth to be credible with engineers: Linux, logs, distributed systems, and ideally ROS or another robotics stack.
• The ability to argue a case from evidence and hold a position with engineering and hardware teams.
• The discipline to protect proactive work from reactive pull.

Responsibilities

• Define and own fleet health: what we measure, what good looks like, and how it is reported.
• Investigate fleet-wide behaviour from logs and telemetry: spot a warning, identify release/config changes, quantify impact and severity.
• Own the fleet's diagnostic data capture — work with teams on rosbag recording rules, log pipelines, telemetry coverage.
• Own alert thresholds, alert quality, resolution and escalation.
• Develop pre-failure detection of robot subsystems.
• Own fleet configuration management: baselines, drift detection, change visibility, drive towards manageable configurations.
• Own fleet data quality and the hardware health foundation: component-level tracking, and a monthly fleet health report to Service and Engineering.
• Preventive maintenance intervals set from fleet data.
• Collaborate with V&V on RC analysis: interpret RC robot signals, catch regressions before rollout, and advise proceed/hold/rollback.
• Build the top-failure-modes register and drive high-impact items to resolution with Engineering.
• Report fleet health to Service, Engineering, Software teams.
• Hire, coach and grow the team; stay hands-on with data and robots.

Skills

Reliability engineering

Telemetry

Observability

SQL

Python

Linux

ROS

System thinking

Tools

Grafana

Prometheus

ROS

Job description

Dexory is building advanced software powering robotic fleets for global logistics. This role owns fleet health, data pipelines, and diagnostic discipline, driving reliability across hardware and software.

You’ll lead data-driven investigations, define thresholds, and work with engineering and hardware teams to prevent failures. You’ll collaborate with teams on telemetry, log quality, and configuration management, while guiding proactive maintenance based on fleet insights.