AI Predictive Maintenance Engineer

Santriya Technologies; Chennai; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Santriya Technologies in Chennai is seeking an AI Predictive Maintenance Engineer to develop and operate predictive maintenance for warehouse, logistics and facility assets by combining condition monitoring, AI anomaly detection and reliability engineering.

You will translate sensor data into actionable maintenance plans, validate AI alerts, coordinate with operations and vendors, and track uptime and maintenance costs.

Qualifications

• Experience in predictive maintenance concepts and reliability engineering.
• Ability to work with sensor data, vibration/temperature datasets.
• Strong collaboration with operations, maintenance and vendors.

Responsibilities

• Define asset criticality, failure modes, sensor/data requirements and predictive maintenance strategy.
• Build/operate condition‑monitoring workflows using vibration, temperature, current, cycle, error and maintenance data.
• Validate AI alerts against failure physics, OEM thresholds and inspection findings.
• Convert credible signals into planned work orders and measure avoided failures.
• Perform root-cause and reliability analysis for repeat or high‑impact failures.
• Improve sensor quality, labeling, failure coding and maintenance data.
• Coordinate engineering, maintenance, operations and vendors on interventions.
• Track precision/recall of alerts alongside uptime, MTBF, MTTR and maintenance cost.

Job description

Job Summary

Santriya Technologies is seeking an AI Predictive Maintenance Engineer to develop and operate predictive maintenance for warehouse, logistics and facility assets by combining condition monitoring, AI anomaly detection and reliability engineering.

Product & documentation operating model

You will be assigned one or more company products, client solutions or operational services. The approved product documentation, SOPs, policies, process maps, knowledge articles, release notes, controls, scripts and AI runbooks are the source of truth. Use only approved enterprise AI tools to retrieve, summarize, draft, classify, prioritize or automate work. Validate material AI outputs against current documentation and authoritative system data, record exceptions, and elevate conflicts or missing guidance. Do not invent product features, prices, customer entitlements, engineering limits, regulatory positions or safety instructions.

Key Responsibilities

• Define asset criticality, failure modes, sensor/data requirements and predictive maintenance strategy.
• Build/operate condition-monitoring workflows using vibration, temperature, current, cycle, error and maintenance data.
• Validate AI alerts against failure physics, OEM thresholds and inspection findings.
• Convert credible signals into planned work orders and measure avoided failures.
• Perform root-cause and reliability analysis for repeat or high-impact failures.
• Improve sensor quality, labeling, failure coding and maintenance data.
• Coordinate engineering, maintenance, operations and vendors on interventions.
• Track precision/recall of alerts alongside uptime, MTBF, MTTR and maintenance cost.

AI-enabled ways of working

• Use approved GenAI copilots, enterprise search/RAG, analytics and workflow agents to reduce repetitive work and improve decision preparation.
• Keep prompts, outputs and automated actions within approved data-access, confidentiality and retention rules.
• Correct inaccurate summaries, classifications or recommendations before they become customer, operational or system records.
• Feed recurring AI errors, knowledge gaps and process friction into product, documentation and control improvement.

Human accountability

AI is a copilot, not the accountable decision-maker. The role holder remains responsible for judgement, quality, privacy, security and appropriate escalation. Credit, fraud blocking, legal/regulatory, financial advice, safety-critical, clinical, employment and other high-impact decisions must follow delegated authority and required human review.

Success Measures

• More failures are prevented before breakdown
• False alarms are controlled
• Planned maintenance share increases
• Reliability and maintenance data quality improve