Senior AI Engineer with Kubernetes

About the Position

We are seeking a highly skilled Senior AI Engineer with Kubernetes and vector database technologies to join our team. In this role, you will design, build, and scale production-grade AI systems, working with cutting-edge LLM frameworks, embeddings, and cloud-native infrastructure to deliver robust and high-performance solutions.

Responsibilities

• Deploy and manage Milvus vector databases, including schema design and index tuning (HNSW, IVF-FLAT)
• Build and maintain embedding and LLM pipelines using OpenAI API, Hugging Face, or Cohere
• Manage Kubernetes clusters, Helm charts, and containerized microservices in production
• Develop and maintain Docker containerization workflows, including multi-stage builds and registry management
• Design and deliver production-grade Python applications, integrating with Go, Java, or C++ where required
• Integrate object storage systems such as AWS S3, MinIO, or Google Cloud Storage
• Evaluate and implement alternative vector database solutions, including Qdrant, Pinecone, and Weaviate
• Collaborate cross-functionally with team members to deliver reliable, scalable AI services
• Ensure operational excellence, observability, and performance of deployed AI workloads

Requirements

• Bachelor's degree in Engineering with 5+ years of relevant experience
• Expertise in Milvus deployment, schema design, and index tuning (HNSW, IVF-FLAT)
• Familiarity with vector database alternatives such as Qdrant, Pinecone, Weaviate, PGVector, or Chroma
• Proficiency in building embedding and LLM pipelines using OpenAI API, Hugging Face, or Cohere
• Skills in Kubernetes cluster management, Helm charts, and containerized microservices
• Background in Docker containerization, multi-stage builds, and registry management
• Production-level Python development along with Go, Java, or C++
• Knowledge of object storage integration, including AWS S3, MinIO, or Google Cloud Storage
• Excellent verbal and written communication skills with strong team collaboration abilities
• Proficiency in English at an Upper-Intermediate level (B2) or higher

Nice to Have

• Experience supporting large-scale RAG applications and multi-agent platforms
• Hands-on familiarity with LangChain, LlamaIndex, or custom pipelines
• Understanding of GPU scheduling, resource optimization, and inference acceleration
• Production experience with hybrid search, metadata filtering, and index tuning
• Implementation of LLM evaluation, governance, tracing, and monitoring tools
• Familiarity with CI/CD pipelines, Infrastructure-as-Code, and cloud-native deployment practices
• Prior work experience in the Oil and Gas industry
• Experience with Dataiku DSS
• Knowledge of SRE practices

We Offer

• Opportunity to work remotely in Georgia, USA, or from any location
• Competitive contractor terms

About the Company

EPAM Systems is a global software engineering and product development company, delivering digital platforms and large-scale systems for the world’s leading organizations.