R

RhythmX AI

AI-powered platform enabling hyper-personalized primary care

Senior Data Engineer

Data EngineeringConfirmed live in the last 24 hours
Full-timeBengaluru, Karnataka, IndiaIn-person

About the Job

Requirements

  • A bachelor's degree in Computer Science, Engineering, Data Science, or a related field is required.
  • At least 6 years of experience in data engineering is required, with proficiency in Python, PostgreSQL or another variant, MongoDB, and Milvus Vector DB.
  • Experience building and managing data pipelines using healthcare data from hospital EHR systems and clinical data sources such as HIEs and clinical standards bodies including CMS and NCQA is required.
  • Demonstrated experience with data lakes and scalable data storage solutions is required.
  • In-depth knowledge of large language models, prompt engineering, embedding techniques, prompt optimization, chunking strategies, generative AI solution performance and scalability, prompt tuning, and context management is required.
  • Hands-on experience applying Python to data engineering through Airflow is required.
  • Hands-on experience with the Azure OpenAI stack for GPT-4, GPT-4o, and o3/o4 models is required.
  • Hands-on experience with Weaviate or Milvus vector databases is required.
  • In-depth knowledge of natural language processing is required.
  • At least one generative AI implementation in production is required.
  • Hands-on experience with LangChain, LlamaIndex, or similar tools and frameworks is required.
  • At least one retrieval-augmented generation implementation is required.
  • Strong exposure to healthcare-domain data workflows is required.
  • Hands-on experience with Fast Healthcare Interoperability Resources and HL7 standards is required.
  • Experience in healthcare data engineering, including extraction, transformation, and loading; normalization; validation; and secure data exchange, is required.
  • Ability to integrate clinical data sources, including EHR and EMR systems, into AI and analytics pipelines is required.
  • Knowledge of tool calling, MCP, retrieval-augmented generation, GraphRAG, and other large-language-model-based retrieval and search is required.
  • Ability to work with onshore and offshore teams is required.
  • Ability to guide the team in problem solving is required.

Responsibilities

  • Develop and optimize data pipelines for efficient extraction, transformation, loading, and management of large-scale healthcare and clinical-guideline data.
  • Manage sensitive healthcare data according to FHIR and HL7 standards, including versioning and variability in Epic Clarity extracts, quality measures, drug formularies, and clinical guidelines, while meeting data regulations and client needs.
  • Use Airflow, Temporal, or similar tools to manage complex data and knowledge workflows for healthcare data processing at scale, including RAG, GraphRAG, tool calling, MCP, search, retrieval, and aggregation.
  • Support data scientists and backend developers by integrating and maintaining data systems across the organization.
  • Support assessment and validation of large-scale generative AI systems using tools such as RAGAs and Opik.
  • Apply technical skills to address healthcare-sector challenges and contribute to solutions that enhance patient care.
  • Maximize the accuracy, minimize the latency, and enhance the performance of generative AI solutions.

Desired Qualifications

  • Expertise with the Azure technology stack to improve data processing and storage capabilities.
  • Experience with clinical data quality management and validation to ensure accurate and reliable data solutions.
  • Knowledge of anomaly and outlier detection techniques in large datasets.
  • Proficiency in querying massive datasets using database queries to drive insights and decisions.
  • Experience with ClickHouse and Snowflake databases or OLAP systems and Starburst data platforms.
  • Experience building and maintaining RESTful web services for data integration and accessibility.
  • Experience with large-scale recommendation systems and managing recommended-item lifecycles that receive end-user clinical feedback.
  • Experience with learning systems, including reinforcement learning that uses feedback as an input to machine learning.
  • Familiarity with large language models, retrieval-augmented generation, and fine-tuning architectures.
  • Expertise in model monitoring and debugging.
  • Expertise in continuous integration and continuous delivery for generative AI solutions.
  • Familiarity with HIPAA-compliant data handling and PHI/PII data governance in healthcare AI/ML systems.
  • Experience fine-tuning models for data applications and healthcare scenarios, such as language models fine-tuned for medication terminologies.

About the Company

RhythmX AI

AI-powered platform enabling hyper-personalized primary care

temp

Company size
11-50
Company stage
Not listed
Total funding
Not listed
Headquarters
Stockholm, United States
Founded
2023

Recently Posted Jobs

Explore more opportunities at RhythmX AI

See more jobs