Senior AI Engineer

About the role

DV Trading is building a centralized AI function to own its model capability and reduce reliance on external providers. The Senior AI Engineer will fine‑tune and distill open‑weight models, operate on‑prem inference infrastructure, and create a model gateway that intelligently routes requests across open and closed providers.

Key responsibilities

• Build and operate a model gateway that routes inference across open and closed models while tracking cost, latency, and quality.
• Design and run distillation pipelines that generate task‑specific training data from frontier model outputs.
• Fine‑tune and evaluate open‑weight models such as Llama, Qwen, or Mistral for DV‑specific tasks.
• Deploy and maintain on‑prem inference infrastructure (vLLM, TGI, or equivalent) on Kubernetes.
• Develop model evaluation frameworks for quality, cost, latency, and regression testing.

Required profile

• 5+ years of software engineering experience with strong Python skills.
• Hands‑on experience fine‑tuning or distilling open‑weight LLMs in production.
• Experience serving LLMs on‑prem using vLLM, TGI, Triton, or similar.
• Proven ability to manage GPU infrastructure and Kubernetes workloads in a production environment.

Required skills

• Python programming
• LLM fine‑tuning and distillation
• Kubernetes and GPU workload management
• On‑prem inference stacks (vLLM, TGI, Triton)
• Model evaluation and regression testing

What we offer

• Discretionary bonus eligibility
• Medical, dental, and vision insurance
• HSA, FSA, and dependent‑care options
• Employer‑paid life and AD&D insurance
• Flexible vacation policy
• Retirement plan with employer match