Описание
EPAM develops enterprise software products, open source solutions, and accelerators. The role supports AI/GenAI applications for Risk-Based Quality Management in clinical trials.
Задачи
•Design and build RAG document ingestion pipelines for clinical trial quality data
•Build and manage vector databases using AWS OpenSearch for RAG-powered AI workflows
•Develop batch and streaming ETL/ELT pipelines from scratch for unstructured clinical data
•Build and expose data APIs for AI application consumption
•Optimize chunking strategies, embedding generation, and retrieval performance for RAG architectures
•Manage data quality, lineage, and governance for AI/ML data pipelines
•Deploy and maintain AWS data infrastructure
•Collaborate with Data Scientists and Backend Developers in an integrated pod team
Требования
•5+ Years of hands-on data engineering experience at scale
•Expertise in RAG document ingestion pipelines, including chunking, embedding, and vector indexing
•Proficiency in AWS OpenSearch as a vector database for RAG workflows
•Advanced proficiency in Python, including SQL and Spark SQL
•Experience transforming unstructured data such as PDF and DOCX for RAG/LLM applications
•Familiarity with AWS Services including S3, Lambda, Glue, Athena, Bedrock, Step Functions, API Gateway, CloudWatch, and DynamoDB
•Knowledge of containerization with Docker
•Ability to build custom pipelines from scratch beyond configuring out-of-the-box services
•English proficiency at B2+ level
Nice to have: pharmaceutical or life sciences background, Snowflake, Pinecone, SageMaker processing jobs, CI/CD tools such as Jenkins and Git/Bitbucket, infrastructure tools such as CDK or Terraform, clinical data standards including CDISC, ADaM, and SDTM.
Условия
No conditions specified
