Senior MLOps Engineer

Stack

Responsibilities

• ▹Build, operationalize, and automate end-to-end MLOps pipelines using Amazon SageMaker Pipelines and MLflow for experiment tracking, model versioning, and registry lifecycle management
• ▹Design, deploy, and manage production SageMaker inference endpoints (real-time, serverless, batch) and Amazon Bedrock API integrations for LLM/SLM deployment with cost controls and latency optimization
• ▹Implement AgentOps / LLMOps frameworks (AgentCore, Bedrock Guardrails, Promptfoo) for multi-agent orchestration, prompt evaluation, safety guardrails, and RAG retrieval pipelines
• ▹Operationalize real-time STT / TTS voicebot pipelines and low-latency speech inference on hybrid/cloud GPU node pools
• ▹Optimize specialized GPU node pools (NVIDIA A100/L40S, EC2 GPU) for Azerbaijani SLM/LLM training, fine-tuning, and scalable inference
• ▹Establish automated CI/CD for machine learning using GitLab CI/CD and Infrastructure-as-Code (Terraform or AWS CDK) with security-gated promotion workflows
• ▹Integrate data de-identification, Format Preserving Encryption (FPE), and tokenization into ML data pipelines so that no raw PII enters the AWS cloud
• ▹Set up telemetry, performance monitoring, model drift detection, and cost anomaly alerting using Amazon CloudWatch, Splunk, and FinOps frameworks
• ▹Collaborate with Data Engineering, AI Architects, and Cloud Teams to integrate vector storage/retrieval (RAG), Apache Spark/EMR-on-EKS runtimes, and local tokenization databases
• ▹Author MLOps runbooks, model deployment procedures, governance documentation, and disaster recovery playbooks

Requirements

• ▹4+ years of hands-on experience in MLOps, DataOps, or Platform Engineering with a primary focus on enterprise Amazon SageMaker (Pipelines, Feature Store, Model Registry, Endpoints)
• ▹Proven experience deploying and operating Generative AI, LLM/SLM models, and Amazon Bedrock services alongside agentic frameworks and RAG pipelines
• ▹Hands-on expertise with MLflow for experiment tracking, model registry, and lifecycle management
• ▹Solid experience in GPU optimization and orchestration (NVIDIA A100/L40S, AWS EC2 GPU instances) for model training and fine-tuning

About the company

The client is the largest mobile network operator in Azerbaijan, offering fixed and mobile telephony, internet, wireless broadband, and value-added services.