Requirements: English
Company: AVENGA (Agencja Pracy, nr KRAZ: 8448)
Region: remote, poland ,
- 5+ years in MLOps, Data/ML Engineering with unstructured data.
- Expert in Python, Git, Bash, and container orchestration (Docker, Kubernetes).
- Experience with chunking strategies, embedding generation, and semantic search.
- Hands-on with OpenSearch and LLM-based retrieval systems (RAG).
- Deep knowledge of AWS (S3, Lambda, Bedrock, SageMaker, CloudWatch).
- Experience in CI/CD (GitLab, ArgoCD) and Infrastructure-as-Code (Terraform, CloudFormation).
- Familiar with MLOps tools: MLflow, Kubeflow, Amazon SageMaker.
- Solid grasp of ML fundamentals: model training/testing, overfitting, classification, clustering.
,[Maintain and optimize MLOps pipelines for unstructured data ingestion (text, PDFs, audio, video)., Enhance chunking, parsing, and metadata enrichment to improve semantic retrieval and LLM performance., Fine-tune vector search and semantic capabilities using OpenSearch and other vector databases., Collaborate with Data Scientists, LLM Experts, and Backend Engineers to scale and improve the system., Operate in a cloud-native AWS environment to ensure security, scalability, and stability., Monitor and troubleshoot complex GenAI systems in production.] Requirements: AWS S3, AWS Lambda, CloudWatch, ArgoCD, Terraform, Testing Additionally: Sport subscription, Training budget, Private healthcare, International projects.