Technology Support II

n. Defines, measure, and report on Service Level Indicators (SLIs) and Service Level Objectives (SLOs) for critical services.

• Supports the deployment, monitoring, and reliability of Large Language Model (LLM) applications and systems utilizing Model Context Protocol (MCP).

• Ensures high availability and reliability of applications running on modern infrastructure such as AWS, Kubernetes, and related cloud-native platforms, and batch processing environments.

• Deploys, monitor, and troubleshoot workloads on AWS, leveraging cloud-native services.

• Manages, monitor, and optimize batch jobs using schedulers like Autosys and Control-M.

• Writes and optimize SQL queries for data extraction, transformation, and reporting.

• Participates in on-call rotations, respond to production incidents, and drive root cause analysis and postmortems. Works closely with data science, engineering, and operations teams to support AI/ML model deployment, LLM workflows, and batch processes.

• Identifies reliability gaps and drive initiatives to improve system resilience, scalability, and efficiency.

Required qualifications, capabilities, and skills

• Formal training or certification on software engineering concepts and 2+ years applied experience

• Proven experience as an SRE, DevOps Engineer, or similar role supporting AI/ML, LLM, and batch processing environments.

• Exposure to Large Language Models (LLMs) and Model Context Protocol (MCP). Proficiency in Python for automation and scripting.

• Strong knowledge of AWS cloud services and infrastructure.

• Experience with SQL and relational databases.

• Hands-on experience with job schedulers (Autosys, Control-M, or similar).

• Familiarity with observability and telemetry tools (e.g., Prometheus, Grafana, CloudWatch, Datadog).

• Understanding of SLI/SLO concepts and their application in production environments.

• Solid troubleshooting and incident management skills.

Preferred qualifications, capabilities, and skills

• Experience supporting AI/ML and LLM model deployment and monitoring.
• Exposure to containerization and orchestration (Docker, Kubernetes).
• Knowledge of CI/CD pipelines and infrastructure as code (Terraform, CloudFormation).
• Experience with other cloud platforms (Azure, GCP) is a plus.