Full Stack Engineer

💼 Full-time🗓 2026-07-31

Core

Building an intelligence platform for middle-market firms, owning the full stack from real-time data pipelines and LLM summarization engines to the user-facing web portal.

Role type

Full Stack Engineer (AI/LLM focus)

Builds

Real-time data pipelines, LLM summarization engines, and user-facing web portals for middle-market firms.

Domain

Artificial Intelligence / Large Language Models / Middle-market SaaS

Deliverable

production ML models | product features

Required skills

TypeScript, Python, SQL, MongoDB, Bash/Shell, Next.js, React, Node.js, Docker, Linux, LLM API integration, Prompt engineering, Agent architecture, Web scraping, Real-time streaming (SSE/WebSockets), Multi-tenant security

Preferred skills

Rust, AWS Bedrock, Google BigQuery, Redis, Signal CLI, Multi-provider LLM routing, Embedding + vector search, Automated briefing pipelines

Technologies

Next.js, React, Tailwind CSS, shadcn/ui, NextAuth.js, Node.js, OpenAI-compatible API, MongoDB Atlas, Docker, Docker Compose, Linux, tmux, EC2, Playwright, BeautifulSoup, AWS, Cloudflare, GitHub Actions, Voyage AI, Fireworks AI

Responsibilities

Own full stack ownership from data model to API to UI to deploy; design async/concurrent systems and data pipeline architecture; execute web scraping at scale with anti-bot evasion; implement real-time streaming for agent responses; debug production multi-stage pipelines; enforce multi-tenant security with data isolation and access control; integrate LLM APIs for chat completions, tool calling, and context management; engineer prompts for summarization and research agents; build multi-step agent architectures with memory patterns and RAG; evaluate AI output for hallucinations and guardrails.

Seniority

Mid-to-Senior, hands-on IC

Rewrite

## About the role San Francisco based start-up Delamain AI is an intelligence platform serving middle-market firms. This engineer owns the full stack — from real-time data pipelines and LLM summarization engines to the user-facing web portal. ## Responsibilities - Full stack ownership: data model → API → UI → deploy (no tier handoff) - Async/concurrent systems & data pipeline architecture (ETL/ELT, deduplication) - Web scraping at scale — anti-bot evasion, government/political sources Playwright,BeautifulSoup) - Real-time streaming — SSE/WebSockets for agent responses - Production debugging across multi-stage pipelines - Multi-tenant security — data isolation, access control, audit logging ## Requirements ### Languages - TypeScript (Expert) — all production frontend/backend code - Python (Proficient) — pipelines, scraping, LLM orchestration - SQL / MongoDB (Proficient) — BigQuery ingestion, aggregation pipelines - Bash/Shell — EC2 ops, cron, deployment scripts ### Frameworks & Infrastructure - Next.js (App Router), React, Tailwind CSS / shadcn/ui, NextAuth.js - Node.js + Server Actions , OpenAI-compatible API (streaming, tool calling) - MongoDB Atlas — document modeling, Atlas Search - Docker / Docker Compose — all services containerized - Linux / tmux — SSH, process management, EC2 service administration ### Engineering Capabilities - Full stack ownership: data model → API → UI → deploy (no tier handoff) - Async/concurrent systems & data pipeline architecture (ETL/ELT, deduplication) - Web scraping at scale — anti-bot evasion, government/political sources Playwright,BeautifulSoup) - Real-time streaming — SSE/WebSockets for agent responses - Production debugging across multi-stage pipelines - Multi-tenant security — data isolation, access control, audit logging ### AI / LLM - LLM API integration — chat completions, tool/function calling, streaming, context management - Prompt engineering for summarization, personas, research agents - Agent architecture — multi-step tool use, memory patterns, RAG - AI output evaluation — hallucination detection, guardrails ## Nice to have - Rust — Core system runs on Rust - AWS Bedrock — Claude 3.x families; cost/quality/latency tradeoffs AWS (EC2, S3), Cloudflare (DNS, tunnels), CI/CD (GitHub Actions) - Google BigQuery — large-scale parallel data ingestion - Redis — caching, job queuing, pub/sub - Signal CLI — secure messaging integration on Linux EC2 - Multi-provider LLM routing (Fireworks AI or similar) - Embedding + vector search (Voyage AI or equivalent) - Automated briefing pipelines — scheduled ingest → summarize → deliver

Sourced via wellfound · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.