Senior Generative AI Specialist for LLM Integration Upgrade

AlphaEdge Tech

Contract · Remote · Flexible hours

About the role

AlphaEdge Tech is revamping its legacy transaction engine, codenamed "PulseCore", to achieve true zero‑downtime releases. As a Generative AI Specialist you will embed large‑language‑model pipelines into the platform to automate code refactoring, schema migration scripts, and real‑time anomaly detection during live traffic.

Key responsibilities

• Design and fine‑tune LLM prompts that generate safe migration code for PostgreSQL schemas in the PulseCore module.
• Integrate LangChain‑based agents with the CI/CD pipeline to auto‑generate unit tests for newly refactored services.
• Build a Flask micro‑service that streams model inferences to the existing monitoring dashboard with zero impact on latency.
• Collaborate with DevOps to containerize the AI inference layer using Docker and orchestrate with Kubernetes rolling updates.
• Document prompt engineering patterns and version control them in a dedicated Git repo for auditability.

Must-have skills

• Deep experience with LLM fine‑tuning (e.g., GPT‑4, LLaMA) and prompt engineering.
• Proficiency in Python for model serving and data pipelines.
• Strong JavaScript knowledge for front‑end integration of AI‑driven features.
• Hands‑on with REST API design, authentication, and performance testing.
• Familiarity with Kubernetes rollout strategies and zero‑downtime deployment patterns.

Nice to have

• Experience with MLOps tools such as MLflow or DVC.
• Background in legacy system modernization projects.