Full Stack AI Engineer | Onsite in San Francisco | Local Candidates Only, 5

Software Placement Group; San Francisco (CA); On-site; USD 140,000 - 230,000; Full time

Job summary

Software Placement Group is seeking a Full Stack AI Engineer in San Francisco to turn ideas into production-ready AI-native products. You will work with founders to shape the tech foundation, build frontend and backend, and integrate LLMs and AI agents.

You will own end-to-end development from zero to one, focusing on speed, quality, and scalable architectures in a fast-growing startup environment.

Qualifications

• 4+ years of professional software engineering experience.
• Proven experience launching a product from zero to one.
• Strong frontend and backend development skills.
• Experience at an early-stage startup.
• Proficiency in TypeScript, JavaScript, React, Next.js.
• Candidates must currently live in the Bay Area and be onsite in San Francisco.

Responsibilities

• Build, test, launch, and improve full-stack products from zero to one.
• Develop modern frontend applications using React, Next.js, or similar technologies.
• Build backend services, APIs, databases, and integrations.
• Create AI-powered features using large language models and multimodal models.
• Build AI agents that can use tools, complete workflows, and interact with external systems.
• Develop retrieval-augmented generation, embeddings, vector search, and knowledge systems.
• Integrate voice AI, speech-to-text, text-to-speech, or real-time conversational systems.
• Implement model routing, structured outputs, tool calling, and human approval workflows.
• Build evaluation, monitoring, and testing systems for AI performance.
• Improve application speed, reliability, scalability, security, and AI inference costs.
• Work directly with founders, users, and product stakeholders.
• Help make product, architecture, and technology decisions.

Skills

Full-stack development

TypeScript/JavaScript

React/Next.js

Node.js/Python/FastAPI/Go

PostgreSQL/APIs

Cloud deployment

AI model integration

AI agents/RAG/tooling

Embeddings/Vector search

Multimodal AI

Product judgment

Startup pace

Tools

LangGraph

LlamaIndex

Vercel AI SDK

Pinecone

Qdrant

Weaviate

pgvector

Job description

Location: San Francisco, CA (candidates must currently live in the Bay Area) | Schedule: Full-time, onsite five days per week

Overview

An early-stage, cutting-edge AI startup is seeking a Full Stack AI Engineer with strong zero-to-one product-building experience to help build and launch AI-native products from the ground up. This engineer will work closely with the founders to turn ideas into production-ready applications and help shape the company's technical foundation.

What you'll do

• Build, test, launch, and improve full-stack products from zero to one
• Develop modern frontend applications using React, Next.js, or similar technologies
• Build backend services, APIs, databases, and integrations
• Create AI-powered features using large language models and multimodal models
• Build AI agents that can use tools, complete workflows, and interact with external systems
• Develop retrieval-augmented generation, embeddings, vector search, and knowledge systems
• Integrate voice AI, speech-to-text, text-to-speech, or real-time conversational systems
• Implement model routing, structured outputs, tool calling, and human approval workflows
• Build evaluation, monitoring, and testing systems for AI performance
• Improve application speed, reliability, scalability, security, and AI inference costs
• Work directly with founders, users, and product stakeholders
• Help make product, architecture, and technology decisions

Required qualifications

• 4 or more years of professional software engineering experience
• Proven experience building and launching a product from zero to one
• Strong experience across both frontend and backend development
• Experience working at an early-stage startup
• Strong skills in TypeScript, JavaScript, React, and Next.js
• Backend experience with Node.js, Python, FastAPI, Go, or similar technologies
• Experience with PostgreSQL, APIs, cloud infrastructure, and production deployments
• Hands-on experience integrating large language models into production applications
• Experience with AI agents, RAG, tool calling, embeddings, or multimodal AI
• Strong product judgment and the ability to work with limited direction
• Ability to move quickly while maintaining high engineering standards
• Must currently live within a reasonable commuting distance of San Francisco; this role is fully onsite five days per week and is not open to remote, hybrid, or relocation-dependent candidates

Preferred qualifications

• Experience with OpenAI, Anthropic, Gemini, or open-source AI models
• Familiarity with Model Context Protocol and agent orchestration frameworks
• Experience with LangGraph, LlamaIndex, Vercel AI SDK, or similar tools
• Experience with vector databases such as Pinecone, Qdrant, Weaviate, or pgvector
• Experience with voice AI, WebSockets, WebRTC, or real-time streaming systems
• Experience with AI evaluations, observability, prompt injection protection, and model securityExperience with Docker, AWS, Google Cloud, Azure, or serverless infrastructure
• Experience as an early, founding, or first engineering hire

Why this role

This is a chance to work directly with founders at an early-stage AI startup, taking full ownership of building AI-native products from zero to one and shaping the company's technical foundation.