Description

You will design, implement, and operate backend solutions that drive AI adoption, focusing on LLM orchestration and real-time interactions.

This role is hybrid.

Responsibilities

• Design and develop backend services supporting generative AI agents and automating editorial workflows for ingestion, enrichment, and publication.
• Build and maintain AWS microservices using Python and FastAPI, establishing stable contracts and integrating with Java/Spring services.
• Operate LLM and RAG services in production, managing prompt/model versioning while monitoring quality, cost, and latency.
• Modernize editorial systems by enhancing XML/XSLT pipelines, Java/Spring services, and Oracle-backed repositories.
• Collaborate with AI/ML engineers and product managers to deliver generative AI experiences for product and editorial workflows.

Required Skills

• 5+ years building scalable backend systems and APIs.
• 3+ years of experience with Python (FastAPI or similar) and strong relational SQL skills (PostgreSQL/Oracle).
• Practical experience with LLMs/AI agents, orchestration, evaluation, and guardrails.
• Proficiency with AWS services including S3, DynamoDB, ElastiCache, and SQS/Kinesis.
• Experience with CI/CD pipelines using GitHub Actions or CodePipeline/CodeBuild.
• Familiarity with IaC tools such as Terraform or CloudFormation.
• Experience integrating with Java/Spring frameworks (MVC/Web, Boot, Data, JPA/Hibernate).
• Working knowledge of security controls: IAM, KMS, and Secrets Manager.
• Familiarity with developer tooling including Git, Maven, and Gradle.

Key Skills

Education

Any Graduate