Software Engineer, Full Stack

Aifund; Mountain View (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

LearnVector is hiring a software engineer to own end-to-end development of an AI-powered learning platform. You will shape the architecture, build frontend and backend systems, and ensure scalable, streaming AI interactions across sessions.

You will work with a founding team to define deployment patterns, observability, and robust data pipelines, delivering high-quality experiences at scale.

Qualifications

• 4+ years building and shipping production web applications end to end.
• Strong TypeScript/JavaScript and modern web frameworks (React/Next.js) with solid backend engineering (Node or Python).
• Experience owning production systems: deployment, monitoring, incident response, performance.
• Experience integrating LLM APIs into products, including streaming.
• Judgment: make architecture calls under uncertainty and adjust with evidence.

Responsibilities

• Build the product end to end: frontend experiences, backend services, data layer, and deployment.
• Make foundational architecture decisions and revisit them as needed.
• Build the serving layer for AI-driven experiences with streaming responses and state management.
• Set the engineering bar with testing, CI, observability, and safe trade-offs.
• Ship daily alongside a founding team and participate in product decisions.

Skills

AI-native

Web development

TypeScript

React/Next.js

Node/Python

API design

SQL

Production systems

LLM integration

Architectural judgment

Tools

WebSockets

WebRTC

LLM APIs

Job description

About LearnVector

For most of history, great teaching has been scarce. A brilliant teacher who knows you well, adapts to how you learn, and patiently stays with you until you get there - almost no one has had that. AI changes what's possible. LearnVector, founded by Andrew Ng, is building a trustworthy AI guide for learning, with a mission to accelerate human development. We're a small, fast-moving team working on-site in Mountain View, California and backed by a $100 million investment from Coursera.

About the role

You will build our software product end to end - the application learners live in, the backend that serves unique AI-enabled learning experiences at scale, and the infrastructure underneath both. You'll make key architecture and implementation decisions early enough that they'll still matter years from now.

The product is unusual in a specific way: every learner's experience is different, generated and adapted for them, and delivered through long-running relationships rather than stateless sessions. Serving that well is a real systems problem - state and memory over months, streaming AI interactions that feel instant, content pipelines with verification stages, and the observability to know what thousands of concurrent learner sessions are actually doing.

What you will do

• Build the product end to end: frontend experiences, backend services, data layer, and deployment - you'll touch all of it, and own large pieces outright
• Make foundational architecture decisions - and revisit them honestly as reality reports back
• Build the serving layer for AI-driven experiences: streaming responses, session and memory state, background generation and verification jobs, graceful degradation when models misbehave
• Set the engineering bar: testing, CI, observability, and the pragmatism to know which corners are safe to cut at our stage and which never are
• Ship daily alongside a founding team that includes Andrew, with direct exposure to every product decision

What you bring

• AI-native: you default to AI-assisted coding and building automations in everything you do, and you stay current with the newest AI engineering practices because you can't help it
• 4+ years building and shipping production web applications end to end
• Strong TypeScript/JavaScript and modern web frameworks (React/Next.js or similar), plus solid backend engineering (Node or Python), API design, and SQL
• Experience owning production systems: deployment, monitoring, incident response, performance - you've been paged and made the pager quieter
• Experience integrating LLM APIs into products, including streaming, and an informed view of what makes AI products feel great or terrible
• Judgment: you can make an architecture call under uncertainty, state your reasoning in a paragraph, and change your mind when evidence arrives

Nice to have

• Early-stage startup experience - you've been one of the first engineers somewhere and know what that demands
• Real-time or voice interaction experience (WebSockets, WebRTC, audio pipelines)
• Data-pipeline or event-analytics experience
• Consumer-product sensibility: you sweat interaction details users can't name but always feel

What success looks like

In your first 30 days, you will have shipped meaningful product improvements to production and formed a view of where the architecture will bend before it breaks.

In your first 6 months, the platform will be one you're proud of - serving personalized learning experiences reliably, instrumented so the team learns from every session, and structured so a growing team can build on it without asking you first.

Equal opportunity

LearnVector is committed to a workplace of mutual respect and equal opportunity. We hire based on qualifications, merit, and business needs, and do not discriminate on the basis of any characteristic protected by applicable law.

Accommodations

If you need a reasonable accommodation at any point in the application or interview process, we'll work with you. Requests are kept confidential and separate from hiring decisions.