Unlimited Job Postings Subscription - $99/yr!

Job Details

Staff ML Engineer (LLM + Voice, fully remote)

  2025-06-05     PITZ     all cities,AK  
Description:

What is Pitz?

Pitz is an AI-native platform built from the ground up to fix a massive, overlooked problem: car repair.

But this isn't “just another SaaS.” We're building a voice-powered copilot that understands symptoms, sounds, and context — and turns that into decisions: diagnostics, part sourcing, workflow automation, and real-time actions.

We launched in LatAm, but the product is being architected as global infrastructure from day one.

The vision? Fix any car, anywhere, in under 24 hours — no friction, no chaos, no human bottlenecks.

What you'll own:

  • LLM infrastructure: prompt pipelines, embeddings, vector DBs (Pinecone, Weaviate)
  • Multilingual RAG systems trained on thousands (soon millions) of real-world cases
  • Voice-to-intent pipelines using Whisper (or better)
  • Tool-using agents for diagnostics, repair workflows, and procurement
  • Design and scaling of GEO systems (Generative Engineering & Operations) — including voice transcription, contextual recall, agent orchestration, and feedback loops
  • Real-time AI performance loop across text, voice, and structured data
  • End-to-end execution — from prototype to production across markets

You might be a fit if you:

  • Have 7+ years of hands-on experience in ML, NLP, or LLM systems, with at least 2 years focused on applied generative AI
  • Have designed and scaled GEO-like architectures (agentic workflows, multimodal prompts, decision engines)
  • Have shipped LLM-powered products in production
  • Know your way around LangChain, LlamaIndex, and vector search
  • Have built RAG pipelines that actually work in production
  • Can optimize for latency, UX, and cost — not just accuracy
  • Are fluent in English and can communicate in Spanish / Portuguese is a plus
  • Want to build something global, practical, and massively scalable — from the inside out

One last thing — our culture? Ruthlessly focused, low ego, and full of fire

  • You'll not only own the AI/LLM architecture — you'll also elevate the existing team, guide them through new technical frontiers, and build what's missing
  • Yes, you can hire — but this isn't a “hire fast, scale fast” kind of place. We care about keeping the team clean, focused, and truly world-class product
  • And yes — you'll be working directly with a founder who's fun, direct, patient, and knows how to stay out of your way when you're building
  • This isn't polished. It's not perfect. But it's real — and it's working. You won't find this in a job board or a slide deck. This is garage-level grit with global firepower. And if you're not building it with us, you'll be watching it from the outside — wishing you had jumped in when it was still raw.


Apply for this Job

Please use the APPLY HERE link below to view additional details and application instructions.

Apply Here

Back to Search