AI Infrastructure Engineer - Backend & Data

Ant-Tech; New York (NY); Hybrid; Confidential; Full time

Job summary

Ant-Tech in New York City (Hybrid) is seeking an expert Infrastructure / Backend Engineer to design and build production AI systems, scalable backend services, and developer infrastructure for next-generation AI applications.

You will join a fast-moving startup with high ownership and significant impact, working closely with engineering and product teams to deliver features and orchestrate AI deployments.

Qualifications

• 4+ years of software engineering experience.
• Experience shipping production AI agents or AI-powered applications.
• Strong understanding of modern AI models such as GPT-4/4o, Claude, Gemini, or open-source LLMs.
• Strong TypeScript/JavaScript and Python skills.
• Experience building modern web applications and backend services.
• Solid understanding of AI application architecture and LLM integration.
• Excellent problem-solving and communication skills.
• Comfortable working in a fast-moving startup environment.

Responsibilities

• Design and build production-ready AI agents for real-world automation.
• Develop scalable backend services and APIs.
• Build infrastructure for AI applications, including orchestration, observability, and deployment pipelines.
• Collaborate closely with engineering and product teams to rapidly deliver new features.
• Improve developer tooling and internal platforms.
• Evaluate and integrate the latest AI models into production systems.

Skills

AI agent development

TypeScript/JavaScript

Python

Backend services

Problem-solving

Communication

Startup environment

Tools

LangGraph

LangChain

Vercel AI SDK

AWS

GCP

Azure

Job description

Ant-Tech in New York City (Hybrid) is seeking an expert Infrastructure / Backend Engineer to design and build production AI systems, scalable backend services, and developer infrastructure for next-generation AI applications.

You will join a fast-moving startup with high ownership and significant impact, working closely with engineering and product teams to deliver features and orchestrate AI deployments.