Data Scientist III

Position: Data Scientist

Role: Machine Learning & AI

Team: Data Science

Location: Gurgaon

About Tata 1mg

Tata 1mg is a trusted health partner for end consumers and large institutions. Our Mission is to make healthcare understandable, accessible and affordable for all Indians. Over the past three years, we've worked to build a healthcare platform that guides customers to the right and affordable care. Today, Tata 1mg is present in 1000+ cities– And we’re just getting started. Leading the chart as one of the top consumer health platforms through ePharmacy, eDiagnostics, e-consult and offline stores.

Tata 1mg has delivered over 15M ePharmacy orders, 2M eDiagnostics orders & 1M+ organic users/day in 2022 and we are just getting started. Our strongest asset is our 6400+ people enabling us to deliver on our mission consistently.

Know more about us:https: www.1mg.com/aboutUs

Brief about the Team

The Data Science team at Tata 1mg is a dynamic group of experts dedicated to leveraging machine learning and artificial intelligence to revolutionize healthcare. We work closely with various departments to develop innovative solutions that enhance patient care, streamline operations, and drive business growth, making healthcare more accessible and efficient for millions of users. 

What will you do: 

• Problem Definition and Solution Design

• Translate business and user needs into well-defined data science problems.

•  Architect solutions for Gen AI agents, autoregressive digital twins.

• Define the data science roadmap and align it with Tata 1mg’s strategic objectives.

 Data Engineering

•  Collaborate with data engineers to collect, process, and integrate diverse data sources.

• Ensure data quality by addressing missing, inconsistent, or unstructured data challenges.

 Model Development

• Build an LLM/VLM or leverage a pretrained LLMs/VLMs to interpret EHRs effectively.

•  Develop an autoregressive model for a health digital twin to forecast future health outcomes.

• Create recommendation systems that propose evidence-based lifestyle and medical interventions, leveraging the digital twin to simulate their impact.

Model Evaluation and Validation

• Assess model performance using relevant metrics (e.g., accuracy, precision, recall) and ensure robustness.

• Validate models with real-world health data to confirm generalizability and reliability.

Integration and Deployment

• Work with software engineers to deploy models, ensuring scalability and performance in production.

• Collaborate with UX designers to present complex health insights in an intuitive, user-friendly manner.

 Monitoring and Maintenance

• Establish monitoring systems to track model performance and detect drift over time.

• Update models as new data becomes available or when performance metrics indicate a need for improvement.

 Collaboration and Communication

• Partner with cross-functional teams, including product managers, engineers, and healthcare professionals, to ensure seamless execution.

• Clearly communicate technical concepts, model insights, and recommendations to both technical and non-technical stakeholders.

Research and Innovation

• Stay abreast of advancements in data science, healthcare analytics, and predictive modeling to enhance the platform.

• Experiment with innovative techniques (e.g., explainable AI, causal inference) to improve accuracy and user trust.

What we are looking for:

 Technical Skills

• Proficiency in Python, Hands-on experience with machine/deep learning frameworks (e.g., TensorFlow, PyTorch, scikit-learn).

• Expertise in data processing libraries (e.g., Pandas, NumPy).

• - Knowledge of Transformers(LLMs, VLMs and other foundational models for time series etc) to leverage unstructured info from EHRs and wearables.

• Familiarity with data visualization tools to present health insights effectively.

 Domain Knowledge

• Basic understanding of healthcare and medical terminologies.(SNOMED, LOINC etc)

 Analytical Skills

• Strong problem-solving skills to address complex data science challenges in healthcare.

• Ability to analyze and interpret diverse health data to derive actionable insights.

•  Experience with explainable AI to ensure model transparency and user trust.

• Familiarity with causal inference or simulation modeling to enhance predictive accuracy (preferred).

•  Communication and Collaboration

• About Company

  1mg is an online healthcare platform offering services like e-pharmacy, lab diagnostics, and online doctor consultations. Now a part of Tata Digital, it aims to make healthcare affordable and accessible across India. It also provides reliable health content and medicine information.