Senior Generative AI Specialist for LLM Integration Sprint

Pinecrest Systems

Contract · Remote · Flexible hours

About the role

Pinecrest Systems is launching a brand‑new AI‑driven collaboration suite called "Nimbus Hub" for its remote‑first SaaS platform. As a Generative AI Specialist you will shape the core LLM pipelines that power real‑time content creation, summarisation, and intelligent assistance across the product.

Key responsibilities

• Design and implement a custom GPT‑based generation engine using LangChain and Azure OpenAI, targeting a MVP demo within 6 weeks.
• Build end‑to‑end data preprocessing pipelines in Python for domain‑specific fine‑tuning, leveraging Hugging Face Datasets.
• Integrate the LLM service with the existing Node.js backend via secure REST APIs and JWT authentication.
• Set up CI/CD for model artefacts using GitHub Actions and Docker, ensuring reproducible deployments to Kubernetes.
• Collaborate with product managers to define prompt templates and evaluation metrics for relevance and latency.
• Monitor model performance in production with Prometheus alerts and conduct weekly bias audits.

Must-have skills

• Deep experience with large language models (GPT, LLaMA) and prompt engineering.
• Proficiency in Python for model training, inference, and API development.
• Strong JavaScript/Node.js background for integrating AI services.
• Hands‑on knowledge of REST API design, security, and versioning.
• Familiarity with cloud AI platforms (Azure, AWS) and container orchestration.

Nice to have

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