Autonomous AI Engineer - Build Next-Gen Desktop/Web Agents

Zyphra; San Francisco (CA); On-site; USD 150,000 - 210,000; Full time

Benefits offered by this job

Relocation and immigration support ona

In-office snacks and meals

Unlimited PTO and company holidays

Job summary

Zyphra in San Francisco is seeking an AI Engineer to help build Agentic Systems and web-navigation agents. You will work on desktop and browser interfaces, secure sandboxing, and large-scale document search, integrating LLMs and vision models for autonomous tasks.

You will design and implement agent interactions with browsers, OS APIs, and enterprise file systems, develop retrieval pipelines, and ensure production-grade ML systems with robust security.

Qualifications

• Proficient in Python with ML-driven application design and debugging.
• Experience with Windows and macOS APIs for screen reading and file interaction.
• Experience across the full ML stack from model integration to serving infrastructure.
• Experience building or integrating retrieval-augmented generation (RAG) systems.
• Familiarity with vector databases and large-scale document indexing.
• Knowledge of web automation tools and headless browser environments; understanding sandboxed or containerized compute environments with strict access controls.
• Background in HCI or interest in building intuitive agent interfaces that extend human capabilities.

Responsibilities

• Design and implement an agentic system capable of interacting with browsers, operating systems, and enterprise filesystems.
• Building search and retrieval pipelines across large-scale structured and unstructured data.
• Integrating LLMs, vision models, reinforcement learning, and scaffolding frameworks for autonomous, multi-step decision-making.
• Engineering secure virtualized runtimes and backend services for agent execution.
• What matters most is your drive to build production-grade ML systems that push the boundary of what software agents can do.

Skills

Python

ML systems

LLM integration

Vector databases

Web automation

HCI interest

Debugging ML apps

Tools

RAG integration

Headless browsers

Sandboxed compute environments

Job description

Zyphra in San Francisco is seeking an AI Engineer to help build Agentic Systems and web-navigation agents. You will work on desktop and browser interfaces, secure sandboxing, and large-scale document search, integrating LLMs and vision models for autonomous tasks.

You will design and implement agent interactions with browsers, OS APIs, and enterprise file systems, develop retrieval pipelines, and ensure production-grade ML systems with robust security.