You are viewing a preview of this job. Log in or register to view more details about this job.

AI Engineer

Roadrunner AI
Email

AI Engineer (Full-Stack, Research Infrastructure) – Roadrunner AI 

Location: Remote  
Type: Full-time 

 

🔎 Overview 

Roadrunner AI is building the modern operating system for scientific research — unifying semantic search, AI-driven analysis, automated extraction, agentic workflows, literature synthesis, and a next-generation Evidence Graph powered by massive scientific datasets. 

We’re hiring a mid-level AI Engineer who is both full-stack and research-literate, comfortable working in a fast-moving early-stage environment, and able to support the entire platform across our Google Cloud infrastructure. This engineer will help build, maintain, and scale our FAISS-based OpenAlex index, develop our Evidence Graph from the ground up, and implement the agentic systems that power our research automation tools. 

This is not an architect role, but it is a high-ownership position: you'll work closely with the CTO in making architectural decisions, planning work, and implementing systems with minimal supervision. 

🎯 What You’ll Do 

Platform Engineering (Full-Stack) 

  • Develop and maintain features across our React/TypeScript frontend and Node.js backend services. 
  • Build and maintain APIs for research tools, partner integrations, indexing, and graph operations. 
  • Manage platform-wide observability, debugging, and reliability improvements. 
  • Work autonomously on scoped features from concept → implementation → iteration. 

Google Cloud Platform (GCP) Infrastructure 

You will actively work across the full Google ecosystem that powers Roadrunner: 

  • Vertex AI (models, embeddings, pipelines) 
  • Cloud Run (containerized services) 
  • Cloud SQL (PostgreSQL) 
  • BigQuery (index + evidence graph analytics, large-scale data ops) 
  • Cloud Functions 
  • Cloud Storage (dataset + model storage) 
  • VPC, IAM, networking, service accounts 

Responsibilities include configuration, troubleshooting, deployment, and continuous improvement. 

FAISS Index & Research Retrieval Systems 

  • Manage, update, and troubleshoot our FAISS OpenAlex index (on Vertex). 
  • Expand indexing capabilities, mappings, shard management, ingestion scripts. 
  • Build API layers for internal and partner use (search, RAG, embeddings, metadata). 
  • Improve retrieval performance and result quality. 

Evidence Graph (Foundational Engineering) 

You will help build the Evidence Graph architecture from scratch, including: 

  • schema + ontology design 
  • entity extraction + relationship mapping 
  • ingestion pipelines (structured + unstructured) 
  • graph storage + query patterns 
  • APIs for internal/partner access 
  • integration into platform tools and dashboards 

Experience with data ingestion, mapping, classification, or graph-like modeling is expected. 

n8n + Agentic Automation Systems 

Must have hands-on experience building: 

  • n8n workflows from scratch 
  • n8n MCP integrations (tool creation, agent interactions) 
  • asynchronous job orchestration 
  • research extraction pipelines 
  • automations that utilize LLMs to transform, validate, and route data 

You’ll support and build multi-agent systems for extraction, synthesis, writing workflows, and systematic review automation. 

Research Workflow & Domain Understanding familiarity is a plus but not required 

API Integrations for Partners 

  • Build and maintain secure APIs that allow partners to access:  
  • our platform features 
  • OpenAlex FAISS index 
  • Evidence Graph 
  • agentic workflows 
  • Implement scalable webhook and callback systems. 
  • Collaborate with partner teams to design robust integration pathways. 

 

🧠 Required Experience 

Technical Skills 

  • TypeScript + Node.js (strong proficiency) 
  • React (mid-level proficiency) 
  • Google Cloud Platform (Vertex AI, Cloud Run, Cloud SQL, GCS, BigQuery) 
  • FAISS (operational knowledge + ability to maintain/update) 
  • Python (data ingestion, embeddings, automation scripts) 
  • Experience working with LLM APIs, RAG, and agentic workflows 
  • Strong API development experience (RESTful APIs, webhooks, auth patterns) 
  • Hands-on experience building n8n workflows and MCP tools 
  • Docker/containerized development environments 

Soft Skills & Working Style 

  • Self-starter who can identify, plan, and implement without constant supervision 
  • Comfortable with rapid iteration and emerging technology adoption 
  • Thrives in constantly changing priorities of early-stage startups 
  • Excellent written and verbal communication skills 
  • Highly adaptable, proactive, pragmatic, and mission-driven 
  • Comfortable working directly with CTO on architecture, planning, and troubleshooting 

Growth Potential 

  • No initial people management responsibilities 
  • Ability to grow into technical lead as team scales