Senior AI Infra & Optimization Engineer - Remote

Vantaca + HOAi; Palo Alto (CA); Hybrid; USD 200,000 - 260,000; Full time

Benefits offered by this job

Medical, Dental, Vision insurance

401K with company match

Remote Flexible

Job summary

HOAi, the fast-growing AI workforce platform acquired by Vantaca, seeks a Senior AI Infrastructure and Optimization Engineer in the Palo Alto area. You will own the systems, experiments, and feedback loops that drive millions of AI tasks from model selection to routing and execution design, primarily using TypeScript.

Build observability, evaluation suites, and optimization loops to maximize task success per dollar while meeting latency and reliability targets.

Qualifications

• Experience building production systems that use LLMs or other ML models.
• Strong software engineering skills in TypeScript and Node.js.
• Experience operating high-volume or high-reliability services.
• Experience designing and running rigorous model evaluations.
• Strong SQL and data-analysis skills.
• Experience building optimization, search, experimentation, or feedback-loop systems.

Responsibilities

• Own infrastructure to measure, operate, and improve millions of AI tasks.
• Build TypeScript services and libraries for model execution, routing, retries, and outputs.
• Instrument workflows for quality, latency, reliability, token usage, and cost.
• Define durable schemas for tasks, evaluations, experiments, and results.
• Design safe rollout/rollback strategies and monitor production changes.
• Develop evaluation suites and deterministic checks aligned with production outcomes.
• Collaborate with platform and product engineers to enable cross-team adoption.

Skills

TypeScript

Node.js

Production systems

SQL

Data analysis

Experimentation

AI/ML experience

Education

B.S./M.S. in CS or related

Tools

OpenAI API

Anthropic API

Google models

TensorRT-LLM

Open-weight models

Job description

HOAi, the fast-growing AI workforce platform acquired by Vantaca, seeks a Senior AI Infrastructure and Optimization Engineer in the Palo Alto area. You will own the systems, experiments, and feedback loops that drive millions of AI tasks from model selection to routing and execution design, primarily using TypeScript.

Build observability, evaluation suites, and optimization loops to maximize task success per dollar while meeting latency and reliability targets.