LLM/ML team support

Intent:
Provide maintenance support to ML Ops team

Key Responsibilities:

User-Level Support
- Monitor Slack channels
- Identify common issues and start building a support playbook and a user knowledge base
- Feature requests (User level)
- Access requests (LLM Access, new Models)
- Inquiries: Chargeback, EWI Process, Risk / Cyber gates
- Assistance: Onboarding, Usage (API, SDK)
- Redirection: potentially "low effort" questions to appropriate support channels (i.e. Exchange Gateway questions get redirected to appropriate slack channel)
- Education (ML - LLM Prompting)
- Intake processing (Immerse usage, orchestrating the intake to Product/TPM)
- Route Escalations, Issue handling and resolution
- Self-service documentation design and with FAQs page

Project Support
- Tracking - attend meetings, track rapidly changing documents and handle new requests coming in
from customer use cases

Tasks
- New feature requests
- Capacity / Demand Tracking: customer capacity requirements and projections
- Inquiries and Escalations at project level
- Reporting (updating customer tracking documents)
- Handling inquiries and escalations from the Developer Assist team.

Maintenance
- Standard model deployment (need to change X to instance type Y)
- New model deployment
- API management (this could be cleaned up)
- Documentation (Change Log, Release Notes, Onboarding, Usage)
- Do we need a whole set of documentation for IaaS?
- Internal Developer Documentation
- Functional testing on API deployment

Required Skills and Qualifications:
- AI/ML - SageMaker Inference, TensoRT, TGI
- Cloud/DevOps - AWS, Kubernetes, Jenkins, EC2 instance types
- Other - Golang, Python, YAML
- Independent and proactive worker
- Curious and fast learner
- Strong critical thinking skills