Data Engineer — AI-Powered

Job Title: Data Engineer — AI-Powered Healthcare Agents

Location-Malad-W (Mindspace) Mumbai

Contact-8652656202 (for more information)

We are building an intelligent AI Agent platform that connects seamlessly with major Electronic Health Record (EHR) and Practice Management Systems (PMS) to automate complex healthcare processes.

We’re seeking a Data Engineer who will design, implement, and maintain the data pipelines, integration layers, and analytics infrastructure that power these AI-driven interactions. This role sits at the intersection of data infrastructure, healthcare interoperability, and AI enablement

Key Responsibilities

· Design, build, and maintain scalable ETL/ELT pipelines for ingesting and processing data from multiple EHR and PMS systems.

· Develop and manage data ingestion adapters using FHIR, HL7v2, CCD, and custom APIs.

· Implement robust data normalization and validation layers to ensure consistent patient, appointment, and provider data across systems.

· Support the real-time and batch data flows that feed the Agent’s AI decisioning engine.

· Collaborate with developer team to supply clean, well-structured data for voice, text, API and email workflows.

· Enable contextual data access for large language models (LLMs) and conversational agents.

· Integrate with data stores used for prompt enrichment, audit trails, and training data curation.

· Ensure compliance with HIPAA, HITECH, and SOC 2 standards in all data handling.

· Implement audit trails, data masking, and encryption for PHI/PII data.

· Contribute to documentation for data lineage, schema evolution, and data quality metrics.

· Work closely with backend developers, and DevOps teams to align on data schemas, APIs, and infrastructure automation.

Required Skills G Ǫualifications

· Bachelor’s or Master’s degree in Computer Science, Data Engineering, or a related field.

· 3+ years of hands-on experience building data pipelines or integrations in healthcare or regulated domains.

· Proficiency with:

o Python, SǪL, and ETL frameworks

o RESTful healthcare APIs

o Cloud Platforms like AWS

· Experience in message queue systems (Kafka, RabbitMǪ, SǪS) for event-driven pipelines.

· Strong grasp of data modeling, schema design, and metadata management.

Preferred Skills

· Familiarity with LLM or conversational AI pipelines (e.g., data preparation for retrieval-augmented generation or prompt engineering).

· Prior work in healthcare SaaS or digital health platforms integrating with multiple EHR systems.

Job Type: Full-time

Pay: ₹900,000.00 - ₹1,100,000.00 per year

Benefits:

• Health insurance
• Provident Fund

Experience:

• Kafka, RabbitMǪ, SǪS: 4 years (Required)
• Grasp of data modeling, schema design, and metadata mgmt: 4 years (Required)

Work Location: In person