Senior Generative AI Specialist Needed for Cloud-Native RAG Pipeline Build

BlueSky Ventures

Contract · Remote · Flexible hours

About the role

BlueSky Ventures is building a next‑gen mobile experience that will launch on the app store next quarter. As a Generative AI Specialist you will align the AI backend with the mobile front‑end, ensuring the new "Nimbus Sync" module delivers real‑time content generation and personalization. The project demands tight integration between cloud LLM services and on‑device inference for a seamless user journey.

Key responsibilities

• Design and implement the LLM inference pipeline using TensorFlow Serving and Docker for the Nimbus Sync module.
• Create RESTful endpoints in FastAPI that mobile clients will call for on‑demand text generation.
• Optimize prompt templates and fine‑tune a GPT‑Neo model to meet latency <200ms on target devices.
• Collaborate with iOS/Android engineers to embed token‑level streaming responses into the app UI.
• Set up CI/CD for model versioning and automated regression testing using GitHub Actions.
• Document API contracts and performance benchmarks for each sprint milestone.

Must-have skills

• Deep expertise in generative LLM architectures and prompt engineering.
• Proficiency with Python, FastAPI, and Docker containerization.
• Experience deploying models on cloud (AWS/GCP) and edge environments.
• Strong grasp of REST API design and performance tuning.
• Track record of delivering AI features for mobile applications.

Nice to have

• Knowledge of MLOps tools such as MLflow or Kubeflow.
• Familiarity with mobile SDKs for on‑device inference.