Data Scientist

Halyard Health; Pune District; On-site; INR 1,500,000 - 3,800,000; Full time

Job summary

Accendra Health is seeking a skilled Data Scientist to develop and optimize ML models, with a strong focus on time-series forecasting, feature engineering, and evaluation. The role involves building scalable data pipelines with PySpark, SQL, and cloud-based tools to integrate large datasets across domains.

You will work closely with cross-functional teams, deploying models to production, monitoring performance, and communicating insights to both technical and non-technical stakeholders.

Qualifications

• Proficiency in Python, PySpark, and SQL for ML and data work.
• Experience with time series forecasting and feature engineering.
• Knowledge of data modeling, evaluation metrics, and model deployment.

Responsibilities

• Develop and optimize ML models with focus on time series forecasting.
• Build and maintain data pipelines using PySpark, SQL, and cloud solutions.
• Evaluate model performance with metrics like MAPE, RMSE, R² and iterate.
• Collaborate with stakeholders to ensure alignment with business goals.
• Deploy, monitor, and improve models in production and present findings.

Skills

Python

PySpark

SQL

Time Series

Feature Eng

Model Eval

Data Pipelines

Cloud (GCP)

ETL Tools

Palantir Foundry

Tools

Boomi

SnapLogic

SSIS

Palantir Foundry

BigQuery

Vertex AI

Google Colab

AutoAI

Job description

At Accendra Health, we understand that healthcare is complex, and we’re here to make it easier. We help deliver care beyond traditional settings, making essential products and services more accessible through every stage of life. As part of the care team, our teammates play a critical role in delivering personalized, long-term care for the patients we serve. With deep expertise promoting health outside the hospital and a presence in communities nationwide through our Apria and Byram Healthcare brands, Accendra Health does more than just deliver the essentials. If you’re interested in meaningful work with impact, explore our career opportunities and join us in our purpose of Bringing Care To Life™. We are seeking a highly skilled Data Scientist with a strong background in machine learning, data engineering, and model optimization. The ideal candidate should be proficient in Python, PySpark, and SQL, experienced in time series forecasting, feature engineering, and data model performance evaluation, and capable of working with large-scale data integration projects across various domains. A large part of this role involves building machine learning models that not only meet but exceed user expectations, driving measurable value for the business. The candidate will need to have a strong grasp of data model optimization, feature engineering, and model evaluation metrics to ensure high-performance solutions. This role also requires experience with cloud platforms, ETL tools, data transformation processes, and working with structured and unstructured data. While not required, familiarity with object‑oriented programming languages (C#, Java, JavaScript) is a plus. Strong communication skills are essential for collaborating with cross‑functional teams and presenting findings effectively.

Key Responsibilities

• Develop and optimize machine learning models with a focus on time series forecasting and predictive analytics.
• Perform feature engineering and data model optimization to enhance model accuracy and efficiency.
• Continuously evaluate model performance using metrics such as MAPE, RMSE, R², and adjust strategies accordingly.
• Build and implement data pipelines using PySpark, SQL, and cloud‑based solutions for seamless data integration.
• Work on large‑scale data integration projects, leveraging tools such as Boomi, SnapLogic, SSIS, or Palantir to extract, transform, and load data.
• Utilize Palantir Foundry, Google Cloud, AutoAI, and Google Colab for data modeling, processing, and automation.
• Design and maintain data warehouse solutions to support advanced analytics and business intelligence.
• Perform complex data transformations using SQL queries and data objects to support AI/ML‑driven initiatives.
• Collaborate closely with business stakeholders to ensure models align with user expectations and business objectives.
• Deploy, monitor, and continuously improve machine learning models in production environments.
• Communicate technical findings and insights effectively to both technical and non‑technical audiences.

Required Skills & Qualifications

• Proficiency in Python, PySpark, and SQL for data analysis, feature engineering, and model development.
• Expertise in time series forecasting models, including ARIMA, Prophet, LSTMs, and ML‑based approaches.
• Strong experience in data model optimization, feature engineering, and performance evaluation.
• Deep understanding of ML model evaluation metrics and best practices in improving model accuracy.
• Hands‑on experience in data engineering, working on data pipelines, ETL, and data transformation projects.
• Experience using Boomi, SnapLogic, SSIS, or Palantir for data integration.
• Proficiency in cloud computing, particularly Google Cloud (BigQuery, Vertex AI, Cloud Functions, etc.).
• Experience with Palantir Foundry for data processing, analysis, and visualization.
• Ability to optimize and query large‑scale datasets using data lakes and relational databases.
• Familiarity with AutoAI for automated model selection and hyperparameter tuning.
• Experience with Google Colab for collaborative machine learning development.
• Excellent problem‑solving and communication skills, with the ability to convey complex concepts to business stakeholders.

Preferred Qualifications

• Experience with MLOps for continuous deployment, monitoring, and retraining of ML models.
• Knowledge of business intelligence and reporting tools for data visualization.
• Background in supply chain, logistics, or operational forecasting.
• Experience in both batch and real‑time data processing architectures.
• Ability to optimize SQL queries and data transformations for performance improvements.
• Familiarity with object‑oriented programming languages such as C#, Java, or JavaScript (not required but beneficial).

Accendra is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, national origin, sex, sexual orientation, genetic information, religion, disability, age, status as a veteran, or any other status prohibited by applicable national, federal, state or local law.

Accendra is not accepting unsolicited assistance from search firms for this employment opportunity. Please, no phone calls or emails. All resumes submitted by search firms to any employee at our Company via email, the Internet, or in any form and/or method without a valid written search agreement in place for this position will be deemed the sole property of our Company. No fee will be paid in the event the candidate is hired by our Company as a result of the referral or through other means.