Senior Generative AI Specialist – Prompt Reliability

CoreData Systems

Contract · Remote · Flexible hours

About the role

CoreData Systems is building the next‑gen analytics backbone for its operations teams. As a Generative AI Specialist you will drive the creation of a data‑pipeline enablement module called PulseStream, turning raw logs into actionable insights through LLM‑augmented analytics. The focus is on rapid prototyping, model integration, and delivering a production‑ready pipeline within a tight timeframe.

Key responsibilities

• Design and implement the PulseStream pipeline using Apache Airflow and Kafka for real‑time ingestion.
• Fine‑tune LLMs (e.g., Llama‑2, GPT‑4) on internal operational datasets to generate predictive alerts.
• Develop RESTful micro‑services in Python Flask that expose model inference endpoints to ops dashboards.
• Set up MLOps CI/CD with GitHub Actions, Docker, and Kubernetes for automated model rollout.
• Collaborate with data engineers to create feature stores in Snowflake and validate data quality.
• Deliver weekly sprint demos and documentation for non‑technical stakeholders.

Must-have skills

• Deep experience with LLM fine‑tuning and prompt engineering.
• Strong Python development, including Flask/FastAPI.
• Proficiency in building and orchestrating data pipelines (Airflow, Kafka).
• Hands‑on MLOps using Docker, Kubernetes, and CI/CD tools.
• Ability to translate business metrics into model evaluation criteria.

Nice to have

• Familiarity with Snowflake or BigQuery data warehouses.
• Experience in operations analytics or monitoring dashboards.