Production experience deploying Claude or OpenAI in live systems.
Experience with retrieval-augmented generation (RAG) systems, including embeddings, retrieval, chunking, and context handling.
At least 3 years of experience with TypeScript and Node.js.
2–3 years of experience building end-to-end production systems spanning backend services, AI pipelines, and frontend dashboards.
Bachelor's degree in Computer Science.
Strong React skills, including component architecture, state management, and performance.
Experience with PostgreSQL queries, migrations, indexing, and query optimization.
Experience integrating APIs using REST, OAuth, and webhooks.
Linux server experience, including SSH, log analysis, debugging, and deployments.
Experience with AWS Lambda, Terraform, and Docker.
Availability during Eastern Time business hours.
Responsibilities
Classify inbound messages by category, intent, urgency, and tone.
Generate contextual responses using enrichment data and implement and tune human approval gates.
Transform raw enrichment data into structured pre-call briefs, generating backgrounds, pain hypotheses, talking points, and rapport hooks.
Maintain and improve the vector database with embeddings, implement markdown-aware chunking strategies, and build asynchronous ingestion workers and semantic search APIs.
Process RSS feeds, social media, video platforms, and search trends; generate reports, forecasts, and content drafts; and run the system autonomously on scheduled jobs.
Extend the multi-agent content system from outline through audit and generation, maintain binary quality gates with citations, and support multiple content formats.
Enrich leads with product data and market insights, build AI scoring and qualification grading systems, and generate automated audit reports.
Build and maintain Slack-integrated operations, automate scheduling workflows, and triage and respond to email autonomously.
Build and improve AI pipelines for client performance insights and improve retrieval quality through re-ranking, chunking, and hybrid search.
Add tool use and function calling for real-time data in LLM pipelines; debug classification errors and improve model accuracy.
Optimize LLM costs, latency, and performance; build dashboards for AI metrics and usage monitoring; and add observability and tracing to AI pipelines.
Expand content quality systems to new formats and use cases.
Desired Qualifications
Experience with multi-agent LLM systems and orchestration.
Expertise with Anthropic Claude, including prompt engineering, tool use, and system prompts.
Experience with vector search and embeddings, such as pgvector or Pinecone.
Experience with Slack API and bot development.
Experience with advertising platform APIs, including Meta, Google, and LinkedIn.
Experience with LLM observability, including cost tracking, tracing, and monitoring.
Experience with AI-assisted development tools such as Cursor and Claude Code.
We're hiring a Full Stack Automation Engineer who operates at the intersection of AI and production systems. You'll build, optimize, and scale AI-powered infrastructure across the full stack — from LLM pipelines and RAG systems to dashboards and background workers. This is a high-ownership role. You won't be handed tickets. You'll be handed problems and trusted to solve them.
WHAT YOU'LL BUILD & SCALE
AI Communication Pipelines
Classify inbound messages by category, intent, urgency, and tone
Generate contextual responses using enrichment data
Implement and tune human approval gates
AI-Powered Sales Intelligence
Transform raw enrichment data into structured pre-call briefs
Generate backgrounds, pain hypotheses, talking points, and rapport hooks
RAG System
Maintain and improve the vector database with embeddings
Implement markdown-aware chunking strategies
Build async ingestion workers and semantic search APIs
Trend Intelligence Engine
Process RSS feeds, social media, video platforms, and search trends
Generate reports, forecasts, and content drafts
Run autonomously on scheduled jobs
Content Quality Pipeline
Extend the multi-agent system (outline → audit → generate)
Maintain binary quality gates (PASS/FAIL with citations)
Support multiple content formats across the pipeline
Automated Lead Qualification
Enrich leads with product data and market insights
Build AI scoring and qualification grading systems
Generate automated audit reports
AI Executive Assistant
Build and maintain Slack-integrated operations
Automate scheduling workflows
Triage and respond to email autonomously
Build and improve AI pipelines for client performance insights