Role Summary
- Improved LLM function-calling accuracy through structured prompt design and response validation.
- Developed APIs and integrated Slack, Google Workspace, and HubSpot automations via FastAPI.
- Migrated ML inference from Replicate to AWS SageMaker to reduce cold-start latency.
Role Summary
- Improved LLM function-calling accuracy through structured prompt design and response validation.
- Developed APIs and integrated Slack, Google Workspace, and HubSpot automations via FastAPI.
- Migrated ML inference from Replicate to AWS SageMaker to reduce cold-start latency.