As a Full-Stack Software Engineer, you will be a core contributor to Zyphra’s Agentic Systems and Interaction projects. You will be at the forefront of building a next-generation desktop and browser-based agent (end-to-end) that can autonomously navigate the web, interact with filesystems, and complete complex user tasks. This role spans agentic orchestration, frontend interfaces, secure sandboxing environments, large-scale document search and retrieval, and language/vision model integration.
Design and implementation of different agentic system designs capable of interacting with browsers, operating systems, enterprise filesystems, collaboration tools, etc.
Building search and retrieval pipelines across large-scale structured and unstructured data
Build the backend layer for RAG systems and other information context management systems required for agents to operate
Integrating LLMs, vision models, reinforcement learning, and scaffolding frameworks for autonomous, multi-step decision-making
What matters most is your drive to build production-grade software
We value velocity and curiosity, especially in fast-moving and ambiguous environments
Proficiency in Python and a deep understanding of building and debugging complex end-to-end applications
Experience working with SaaS environment and production workloads, web interfaces, databases, search engines, and queuing systems
Experience developing browser extensions or automation tools with fine-grained control over the browser (mouse, tabs, DOM)
Understanding of LLMs, prompting techniques, and orchestration frameworks for multi-step reasoning
Ability to work across the whole stack from web interfaces to control plane and data infrastructure like queuing systems, databases, and search indexes
Experience designing or working with secure and virtualized execution environments
Excellent communication and collaboration skills across product, research, and engineering teams
Experience building or integrating retrieval-augmented generation (RAG) systems
Experience working with enterprise security and compliance frameworks (i.e., SOC 2, GDPR, etc.)
Familiarity with embeddings, vector databases and large-scale document indexing
Knowledge of web automation tools and headless browser environments (i.e., Puppeteer, Playwright)
Understanding of sandboxed or containerized compute environments with strict access controls
Comfort designing user-facing agentic workflows and reasoning systems that span multiple modalities (text, vision, actions)
Experience using and fine-tuning models for screen reading, OCR, or UI understanding
Background in HCI or interest in building intuitive agent interfaces that extend human capabilities
Machine Learning experience as a double bonus
Our research methodology is grounded in methodical, step-by-step approaches to ambitious goals. Both deep research and engineering excellence are equally valued
We strongly value new and crazy ideas and are very willing to bet big on new ideas
We move as quickly as we can; we aim to minimize the bar to impact as low as possible
We all enjoy what we do and love discussing AI
Comprehensive medical, dental, vision, and FSA plans
Competitive compensation and 401(k) plan
Relocation and immigration support on a case-by-case basis
In-office snacks and meals provided
Unlimited PTO and company holidays
In-person team in San Francisco with a collaborative, high-energy environment
Job details are sourced from the employer's original posting.
Open job postingAbout the company
Zyphra is an AI research company developing neural network compression and inference technologies for efficient large language models.