Senior LLM Application Engineer (PHP/Laravel) for Production Chat & Reporting at Punch List Digital | Torre

Senior LLM Application Engineer (PHP/Laravel) for Production Chat & Reporting

Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Freelance
Recurrent (~40 hours per week)
Provide your expected compensation while applying
location_on
Remote (specific timezone)
public
GMT-05:00 to GMT-03:00
Shared by
Erick Daniel Peralta Martinez
9 days ago

Responsibilities


Punch List Digital is hiring a Senior LLM Application Engineer to build the chat and reporting systems used by internal teams and clients.What you'll buildProduction LLM-powered chat applicationsAI-generated monthly reports and PDFsLaravel application architectureRetrieval-augmented generation (RAG) workflowsKnowledge Vault retrieval using pgvectorStructured LLM outputs and tool-useVersioned prompt libraries and quality gatesMulti-tenant client data workflowsDurable, observable queue-based processingCore technologyPHP / LaravelLLM APIsAnthropic / ClaudePostgreSQLpgvectorREST / Third-Party APIsRAG / Embeddings / Similarity SearchWhat they're looking for4–6+ years backend engineering experienceStrong PHP & Laravel — Eloquent, queues/jobs, service container & eventsPHPUnit or Pest testing experienceProduction LLM API integrationStructured outputs, tool-use & prompt designThird-party API integrationOAuth, service accounts, pagination and rate-limit handlingStrong PostgreSQL and query optimization skillsPractical RAG experienceStrong written technical communicationHigh standards for data accuracy and production reliabilityPreferred:pgvector in productionAnthropic Claude — tool-use, streaming & prompt cachingGoogle Analytics 4 / Google Ads / SEMrush APIsMonday.com / WhatConvertsMulti-tenant systemsPDF/document generationMarketing / SEO / SEM experienceThis is NOT a model-research role. The focus is on applying LLM capabilities inside a production Laravel application — prompt design, structured outputs, tool-use, retrieval, validation and reliable client-facing AI experiences.