About ITRex
ITRex - AI pioneers who build systems that actually work in the real world, not just in demos. We're 250+ people spread across the US and Europe, creating solutions for companies like Procter & Gamble and Shutterstock. We keep it simple, build it right, and focus on what works.
We're the kind of people who don't ignore messages in Slack, who jump in to help when you're stuck on a problem, and who offer solutions instead of blame when things go sideways. We believe in openness, accountability, and having each other's backs. No office politics, no hidden agendas - just people who care about doing good work together and supporting each other to get there.
You'll work on the C++ layer that powers local AI, porting and enhancing inference engines like llama.cpp or similar, to run efficiently on edge devices. Your focus is on the runtime: making models load faster, run leaner, and perform well across different hardware. You'll ensure that the inference layer is stable, optimized, and ready for integration with the rest of the stack.
This role is for engineers who want to work close to the metal, enabling private and fast on-device AI without relying on cloud infrastructure.
Requirements
Benefits
Why people stay
First, the foundation:
Then, the growth:
Finally, the people:

ITRex is an AI consulting and implementation company that builds systems meant to work in the real world, at scale, and under pressure.
Generative AI is a core focus, but our expertise spans the full AI and data stack — from classical machine learning and computer vision to autonomous agents and data infrastructure. Our solutions aren’t just prototypes. They're built to integrate, scale, and deliver. Leaders come to us to explore what’s possible — and then make it real.
Gen AI Solution Development & Deployment
– LLM integration and deployment (GPT, Claude, Gemini, LLaMA, Mistral)
– Production-grade RAG with proprietary data
– AI copilots for knowledge, support, operations
– SLMs for edge, low-latency, and private environments
– Autonomous agents for multi-step workflows
– Prompt engineering for efficiency and control
AI-Ready Infrastructure & Governance
– Vector DBs and pipelines (Pinecone, FAISS, Weaviate)
– Unstructured data processing and ingestion
– LLMOps for monitoring and observability
– Built-in compliance: HIPAA, SOC2, EU AI Act
Strategic AI Enablement
– Readiness assessments and use case roadmaps
– PoCs with a path to production
– Risk control: retrieval fallback, prompt audits, trust layers
We support clients in healthcare, biotech, pharma, retail, logistics, and manufacturing — where AI must be scalable, accurate, and compliant. With 500+ solutions delivered since 2009, clients like P&G, Shutterstock, WorkFusion, Dollar Shave Club, Turvo, and Noom trust us to deliver AI that works.
Bring us your challenge. Let’s make it real