Data Scientist – Aviation Analytics & Prescriptive AI

ADT Core; Hyderabad; Hybrid; INR 600,000 - 1,200,000; Full time

Job summary

A leading analytics company is seeking a Data Scientist to enhance aviation operations through predictive maintenance analytics. The successful candidate will develop and validate statistical and machine learning models while collaborating with domain experts and software engineers to integrate insights into production systems. Requirements include a relevant degree, 3-6 years of experience, and strong proficiency in Python and data science libraries. This position offers a hybrid work model with opportunities for impactful contributions in the aerospace industry.

Qualifications

• 3-6 years of experience in data science, machine learning, or statistical modeling.
• Strong experience with time-series datasets.

Responsibilities

• Develop statistical and machine learning models for reliability forecasting.
• Define model evaluation frameworks aligned with operational outcomes.
• Analyze operational datasets to detect patterns, anomalies, and emerging risks.

Skills

Python

Machine Learning

Statistical Modeling

Data Analysis

Education

Bachelor's or Master's in relevant field

Tools

NumPy

Pandas

SciPy

scikit-learn

PyTorch

TensorFlow

Job description

Data Scientist – Aviation Analytics & Prescriptive AI

Company: ADTCORE Pvt. Ltd.

Location: Remote / Hybrid (India)

Industry: Aerospace, Aviation Analytics, AI Platforms

Remote Job: Yes

Role Summary

ADTCORE is building Predicta, an AI‑driven prescriptive maintenance platform designed to help aviation operators improve fleet reliability, safety, and operational readiness. We are looking for a Data Scientist who will design and validate analytical models for reliability, time‑series health monitoring, and prescriptive decision support. The role focuses on transforming operational and engineering data into explainable insights that can support maintenance planning, fault detection, and operational decision‑making. You will work closely with domain experts, software engineers, and product leadership to ensure that analytical outputs are scientifically robust, operationally meaningful, and production‑ready.

Key Responsibilities

• Model Development: develop statistical and machine learning models for time‑series analysis, anomaly detection, and reliability forecasting; build models that support prescriptive recommendations, not just predictive outputs; design health monitoring algorithms for operational equipment and complex systems; implement reliability modeling approaches such as survival analysis, degradation modeling, or failure probability estimation.
• Model Validation & Evaluation: define model evaluation frameworks aligned with operational outcomes; develop validation pipelines for testing model accuracy, robustness, and stability; ensure models include confidence scoring, uncertainty estimation, and explainability; perform sensitivity analysis and error diagnostics.
• Data Analysis & Insight Generation: analyze operational datasets and sensor data to detect patterns, anomalies, and emerging risks; translate analytical results into clear insights and decision‑ready outputs; work with engineering teams to integrate models into production systems.
• Data Quality & Governance: define data quality standards for analytical pipelines; establish data validation and monitoring processes; ensure traceability and reproducibility of models and analyses.
• Cross‑functional Collaboration: collaborate with aviation domain experts to ensure models reflect real‑world maintenance practices; work with software engineers to operationalize models within production workflows; contribute to the design of analytics frameworks supporting large‑scale operational deployments.

Required Qualifications

• Bachelor’s or Master’s degree in Data Science, Statistics, Computer Science, Applied Mathematics, Engineering, or related fields.
• 3‑6 years of experience in data science, machine learning, or statistical modeling.
• Strong experience with Python and data science libraries (NumPy, Pandas, SciPy, scikit‑learn, PyTorch/TensorFlow).
• Experience working with time‑series datasets.
• Strong knowledge of statistical modeling, probability theory, and model evaluation techniques.
• Experience with data visualization and exploratory analysis.

Preferred Qualifications

• Experience working with industrial, sensor, IoT, or operational datasets.
• Knowledge of reliability engineering or predictive maintenance.
• Familiarity with survival analysis, anomaly detection, or degradation modeling.
• Experience deploying models in production environments.
• Exposure to large‑scale analytics systems or cloud data platforms.