Senior Generative AI Specialist for Enterprise RAG Pipeline Build

DataPro Services

Contract · Remote · Flexible hours

About the role

DataPro Services is launching a greenfield SaaS platform and needs a Generative AI Specialist to build the core AI engine. You will shape the "Nimbus Composer" module, a next‑gen content generation service that will power the product from day one.

Key responsibilities

• Design and implement large‑language‑model pipelines in PyTorch and TensorFlow for real‑time text generation.
• Integrate LLM APIs (OpenAI, Anthropic) with existing Node.js microservices using REST.
• Develop prompt‑engineering framework and version‑control system for reusable prompts.
• Set up automated evaluation metrics (BLEU, ROUGE, human‑in‑the‑loop) and CI testing in GitHub Actions.
• Deliver a prototype MVP of Nimbus Composer within the first six weeks, including a demo dashboard.
• Document model architecture, data preprocessing steps, and deployment scripts for Docker/Kubernetes.

Must-have skills

• Deep expertise in LLM fine‑tuning and prompt engineering.
• Proficiency with Python, JavaScript, and building REST APIs.
• Experience deploying models on cloud platforms (AWS, GCP) with container orchestration.
• Strong knowledge of data pipelines, tokenization, and inference optimization.

Nice to have

• Background in Retrieval‑Augmented Generation (RAG) techniques.
• Familiarity with MLOps tools such as MLflow or Kubeflow.