Senior AI Infra & Optimization Architect

Vantaca; Palo Alto (CA); On-site; USD 200,000 - 260,000; Full time

Job summary

HOAi, now part of Vantaca, is hiring a Senior AI Engineer, Evaluation & Optimization in the United States. You will own the production AI infrastructure, design evaluation loops, and optimize prompts, model configurations, routing policies, and execution designs to maximize task success per dollar while meeting quality, reliability, and latency targets.

TypeScript is the primary language. This is a production engineering role in a fast-growing company applying AI at scale.

Qualifications

• Strong software engineering skills in TypeScript and Node.js.
• Experience building production systems that use LLMs or other machine-learning models.
• Experience operating high-volume or high-reliability services.
• Experience designing and running rigorous model evaluations.
• Strong SQL and data-analysis skills.
• Experience designing controlled experiments and interpreting noisy results.

Responsibilities

• Build and operate production AI infrastructure for millions of tasks.
• Develop TypeScript services for model execution, routing, retries, and outputs.
• Instrument AI workflows for quality, latency, reliability, token usage, and cost.
• Define durable schemas for tasks, evaluations, experiments, model versions, and results.
• Design evaluation suites, automated graders, and LLM-as-judge evaluations.
• Run model experiments and optimization loops to improve cost and performance.
• Collaborate with platform and product engineers to adopt optimization capabilities across the stack.

Skills

TypeScript

Node.js

LLM APIs

SQL

Data analysis

Job description

HOAi, now part of Vantaca, is hiring a Senior AI Engineer, Evaluation & Optimization in the United States. You will own the production AI infrastructure, design evaluation loops, and optimize prompts, model configurations, routing policies, and execution designs to maximize task success per dollar while meeting quality, reliability, and latency targets.

TypeScript is the primary language. This is a production engineering role in a fast-growing company applying AI at scale.