Senior Generative AI Specialist for Multi-Region Prompt Workflow Automation

TechFlow Inc

Contract · Remote · Flexible hours

About the role

TechFlow Inc is expanding its AI capabilities within a multi‑tenant B2B platform. As a Generative AI Specialist you will lead the delivery of a new "InsightForge" feature that enables dynamic content generation for each tenant. The project focuses on integrating large language models into existing workflows while maintaining strict data isolation.

Key responsibilities

• Design and implement the InsightForge micro‑service using FastAPI and Docker, ensuring tenant‑level isolation.
• Fine‑tune a pre‑trained LLM (e.g., Llama‑2) on domain‑specific corpora and expose it via a secure REST endpoint.
• Develop CI/CD pipelines in GitHub Actions for automated model testing, container builds, and rollout across three cloud regions.
• Collaborate with the product team to define prompt templates and evaluation metrics for each tenant segment.
• Monitor model latency and cost using Prometheus and Grafana, delivering performance reports every sprint.
• Document API contracts, versioning strategy, and rollback procedures for multi‑tenant deployments.

Must-have skills

• Deep experience with LLM fine‑tuning and prompt engineering.
• Proficiency in Python, FastAPI, and container orchestration (Docker/Kubernetes).
• Strong knowledge of REST API design and security best practices.
• Hands‑on experience with CI/CD tools, especially GitHub Actions.
• Ability to work with multi‑tenant architectures and data isolation techniques.

Nice to have

• Familiarity with MLOps platforms such as MLflow or Weights & Biases.
• Exposure to cloud services like AWS SageMaker or Azure AI.