Senior Generative AI Specialist Needed for Secure Prompt Workflow Automation

NovaForge Tech

Contract · Remote · Flexible hours

About the role

NovaForge Tech is launching a greenfield SaaS platform called AuroraPulse, a next‑gen analytics suite powered by generative AI. As a Generative AI Specialist you will shape the core LLM pipelines that drive real‑time insights for a remote‑first user base.

Key responsibilities

• Design and implement a fine‑tuned LLM workflow in PyTorch for AuroraPulse's recommendation engine.
• Develop prompt engineering frameworks using LangChain to support multi‑modal content generation.
• Integrate the model with FastAPI endpoints and secure token‑based authentication.
• Set up CI/CD for model artifacts using GitHub Actions and Docker, delivering weekly builds.
• Collaborate with data engineers to create a streaming data pipeline on Kafka for real‑time model updates.
• Document model versioning and evaluation metrics in Confluence for stakeholder review.

Must-have skills

• Deep experience with large language models (GPT‑4, LLaMA) and fine‑tuning.
• Proficiency in Python, JavaScript, and REST API design.
• Hands‑on knowledge of LangChain, PyTorch, and Hugging Face Transformers.
• Strong background in prompt engineering and evaluation.
• Experience deploying models in Docker/Kubernetes environments.

Nice to have

• Familiarity with MLOps tools such as MLflow or Weights & Biases.
• Exposure to vector databases like Pinecone or Milvus.