About the job
NEORIS, now part of EPAM Systems, is a leading Digital Accelerator dedicated to guiding organizations into the future. With over 20 years of experience, we have established ourselves as trusted Digital Partners for some of the world's most influential companies. Our team of more than 4,000 professionals, spread across 11 countries, thrives in a dynamic, multicultural environment that fosters innovation, continuous learning, and the development of impactful solutions tailored to our clients' needs.
We are seeking a Senior AI Platform Backend Engineer (LLM Specialist) to join our team.
Key Responsibilities:
• Design, implement, and oversee cloud infrastructure on AWS utilizing Infrastructure as Code (IaC) tools such as Terraform or AWS CloudFormation.
• Enhance and manage CI/CD pipelines using tools like GitHub Actions, AWS CodePipeline, Jenkins, or ArgoCD.
• Implement observability solutions including Amazon CloudWatch, Prometheus/Grafana, or ELK for effective monitoring and alerting.
• Support container orchestration environments such as EKS (Kubernetes), ECS, or Fargate.
• Develop backend architecture for AI Verification and Az ChatGPT Services using Python and FastAPI.
• Create and maintain solutions based on Domain-Driven Design (DDD) and Test-Driven Development (TDD) methodologies.
• Develop and manage a LLM-as-a-judge production service to validate AI-generated content employing tools like HuggingFace, Transformers, SpaCy, NLTK, and BM25.
• Optimize model latency utilizing compression strategies such as ONNX and quantization.
• Deploy and manage multi-service AI solutions on Kubernetes with integrated Prometheus and Grafana monitoring.
• Construct CI/CD pipelines for the continuous integration and deployment of AI services.
• Design, develop, and maintain high-load RAG solutions, including ingestion services, message brokers, and retrieval services.

