Senior MLOps Engineer

Description

We are seeking an **MLOps Engineer** to support operations and maintenance of production GenAI and agent-based solutions. The professional will be responsible for executing standard operating procedures (SOPs), monitoring system integrity and performance, and resolving issues using observability tools and logs to ensure reliability, performance, and scalability of AI-powered applications. **Key Responsibilities** Operations and Support * Execute and follow established Standard Operating Procedures (SOPs) for production GenAI and agent-based solutions * Monitor platform integrity, model performance, and inference pipelines * Ensure stability and availability of AI services across all environments Incident Management and Problem Resolution * Investigate and resolve incidents by analyzing logs, traces, and metrics * Perform root cause analysis (RCA) and document findings * Escalate according to defined escalation processes when necessary Observability and Monitoring * Use observability tools (logs, metrics, tracing) to detect anomalies and performance issues * Support continuous improvement of monitoring, alerting, and dashboards * Ensure proper instrumentation of GenAI and ML workloads GenAI and Agent Operations * Support runtime operations of LLM-based applications and agent-driven workflows * Monitor inference performance (latency, throughput, cost) * Ensure compliance with guidelines, reliability standards, and operational best practices Continuous Improvement Practices * Identify opportunities to automate operational tasks and improve efficiency * Contribute to the evolution of Standard Operating Procedures (SOPs), runbooks, and operational frameworks * Collaborate with Engineering and Data Science teams to enhance system reliability. **Work Model: Remote** **English: Advanced** Requirements: * Experience with MLOps, ML systems, or AI platform operations * Strong problem-solving skills using logs and observability tools * Familiarity with cloud environments (e.g., Azure, AWS, GCP) * Understanding of ML pipelines, APIs, and distributed systems * Experience with monitoring tools (e.g., Datadog, Prometheus, Grafana, Azure Monitor) **Desirable** * Experience with GenAI/LLM-based applications * Experience with orchestration tools (e.g., Airflow) * Knowledge of model lifecycle management and deployment patterns * Familiarity with incident management processes (SLA/SLO, on-call, escalation)