Senior AI Engineer: RAG Pipelines, Spark & AWS

EPAM Systems, Inc.; Turkey; On-site; TRY 6,866,000 - 9,809,000; Full time

Job summary

EPAM Systems, Inc. seeks a Senior AI Engineer to design and maintain data pipelines powering AI/GenAI in clinical trial risk management. The role emphasizes RAG ingestion, vector indexing, and building data APIs for AI apps within the RBQM Production Pod.

You will work with data scientists and backend engineers, optimizing retrieval, embeddings, and ETL/ELT pipelines using AWS services and Spark SQL.

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 Python skills, including SQL and Spark SQL.
• Experience transforming unstructured data (PDF, DOCX) for LLM applications.
• Familiarity with AWS: S3, Lambda, Glue, Athena, Bedrock, Step Functions, API Gateway, CloudWatch, DynamoDB.
• Containerization with Docker; building custom pipelines from scratch.

Responsibilities

• Design and build RAG document ingestion pipelines for clinical trial quality data.
• Build and manage vector databases for RAG-powered AI workflows.
• Develop batch and streaming ETL/ELT pipelines from unstructured data sources.
• Expose data APIs for AI application consumption.
• Optimize chunking, embeddings, and retrieval performance for RAG architectures.
• Ensure data quality, lineage, and governance for AI/ML pipelines.
• Collaborate with Data Scientists and Backend Developers in an integrated pod.

Skills

RAG ingestion pipelines

Python

Spark SQL

SQL

AWS OpenSearch

Docker

ETL/ELT

vector indexing

API development

SageMaker processing

Tools

AWS OpenSearch

S3

Lambda

Glue

Athena

DynamoDB

Bedrock

API Gateway

Git/Bitbucket

Terraform

CDK

Snowflake

Pinecone

Job description

EPAM Systems, Inc. seeks a Senior AI Engineer to design and maintain data pipelines powering AI/GenAI in clinical trial risk management. The role emphasizes RAG ingestion, vector indexing, and building data APIs for AI apps within the RBQM Production Pod.

You will work with data scientists and backend engineers, optimizing retrieval, embeddings, and ETL/ELT pipelines using AWS services and Spark SQL.