AI Engineer

Role Overview We are seeking a highly technical Cloud Engineer to build and optimize our Generative AI infrastructure. This role focuses on deploying AWS Bedrock agents, automating workflows with Python , and creating robust observability and billing pipelines for LLM usage. You will be responsible for ensuring that our AI services are not only functional but also cost-effective and highly monitored through advanced logging and alerting.

Key Responsibilities AI Agent Orchestration: Design and deploy specialized agents using AWS Agents for Amazon Bedrock to automate complex multi-step business processes. Observability & Alerting: Build end-to-end \"Data Log\" pipelines. Identify and implement the correct AWS services for alerting (e.g., CloudWatch, SNS, or Lambda) based on log anomalies.

Integration & Middleware: Manage and analyze Mulesoft logs to ensure seamless connectivity between legacy systems and modern AI services. Financial Operations (FinOps): Monitor billing metrics for LLM usage and AWS Bedrock services to prevent cost overruns and optimize token consumption. Python Automation: Write production-grade Python scripts for data processing, agent logic, and infrastructure automation.

Technical Requirements (The \"Must-Haves\") Core AWS AI Services: Hands-on experience with AWS Bedrock and AWS Agent Core logic. Programming: High proficiency in Python (specifically for data manipulation and API integrations). Logging & Monitoring: Deep understanding of log aggregation.

Experience with Mulesoft logs is a significant plus. Alerting Frameworks: Ability to determine which AWS service to use for specific alerts (CloudWatch Alarms vs. EventBridge vs.

Managed Grafana). LLM Knowledge: Understanding of how LLMs work, including tokenization, prompt engineering, and the cost structure of different models.