Senior AI Engineer with Spark, AWS Services

EPAM Systems Inc; United States; Remote; USD 150,000 - 210,000; Full time

Job summary

EPAM Systems is seeking a Senior AI Engineer to design and maintain data pipelines powering AI/GenAI applications for Risk-Based Quality Management in clinical trials.

Focus areas include RAG document ingestion, vector indexing, and AWS-based data infrastructure. The role requires strong Python, Spark SQL, and OpenSearch skills and collaboration with a cross-functional team in a fast-paced environment.

Qualifications

• 5+ years of hands-on data engineering experience at scale.
• Expertise in RAG document ingestion pipelines (chunking, embedding, vector indexing).
• Proficiency in AWS OpenSearch as a vector database for RAG workflows.
• Advanced proficiency in Python, including SQL and Spark SQL.
• Skills in unstructured data transformation (PDF, DOCX) for RAG/LLM applications.
• Familiarity with AWS Services: S3, Lambda, Glue, Athena, Bedrock, Step Functions, API Gateway, CloudWatch, DynamoDB.
• Knowledge of containerization with Docker.
• Proficiency in English at a B2+ level.
• Nice to have Background in pharmaceutical or life sciences domain.

Responsibilities

• Design and build RAG document ingestion pipelines (chunking, embedding, vector indexing) for clinical trial quality data.
• Build and manage vector databases (AWS OpenSearch) for RAG-powered AI workflows.
• Develop batch and streaming ETL/ELT pipelines from scratch for unstructured clinical data (PDF, DOCX, clinical reports).
• 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 (S3, Lambda, Glue, Athena, Step Functions, DynamoDB).
• Collaborate with Data Scientists and Backend Developers in an integrated pod team.

Skills

RAG pipelines

AWS OpenSearch

Python

SQL

Spark SQL

Unstructured data

Docker

CI/CD

CDK

Terraform

CDISC standards

SageMaker

Snowflake

Pinecone

APIs

English (B2+)

Tools

Snowflake

Pinecone

SageMaker

OpenSearch

Docker

Terraform

CDK

Job description

Introduction

We are seeking a Senior AI Engineer with Spark and AWS Services expertise to join the RBQM Production Pod within the program. You will build and maintain data pipelines that power AI/GenAI applications for Risk-Based Quality Management in clinical trials. This role focuses on RAG document ingestion, vector indexing, and building data APIs for AI applications.

Responsibilities

• Design and build RAG document ingestion pipelines (chunking, embedding, vector indexing) for clinical trial quality data
• Build and manage vector databases (AWS OpenSearch) for RAG-powered AI workflows
• Develop batch and streaming ETL/ELT pipelines from scratch for unstructured clinical data (PDF, DOCX, clinical reports)
• 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 (S3, Lambda, Glue, Athena, Step Functions, DynamoDB)
• Collaborate with Data Scientists and Backend Developers in an integrated pod team

Requirements

• 5+ years of hands-on data engineering experience at scale
• Expertise in RAG document ingestion pipelines (chunking, embedding, vector indexing)
• Proficiency in AWS OpenSearch as a vector database for RAG workflows
• Advanced proficiency in Python, including SQL and Spark SQL
• Skills in unstructured data transformation (PDF, DOCX) for RAG/LLM applications
• Familiarity with AWS Services: S3, Lambda, Glue, Athena, Bedrock, Step Functions, API Gateway, CloudWatch, DynamoDB
• Knowledge of containerization with Docker
• Capability to build custom pipelines from scratch, beyond configuring out-of-the-box services
• Proficiency in English at a B2+ level
• Nice to have Background in pharmaceutical or life sciences domain
• Familiarity with Snowflake, Pinecone (vector DB alternative)
• Knowledge of SageMaker processing jobs
• Skills in CI/CD tools (Jenkins, Git/Bitbucket) and infrastructure tools (CDK or Terraform)
• Understanding of clinical data standards (CDISC, ADaM, SDTM)