Senior/Principal Local LLM & Generative AI Platform Engineer
Core
Build and operate a secure local large-language-model platform for engineering and business teams to use generative AI with proprietary internal data while keeping sensitive information within company-controlled environments.
Role type
Senior/Principal individual-contributor LLM platform engineer
Builds
A modular inference and model-gateway layer with stable APIs, model routing, streaming, concurrency controls, and the ability to change models or serving backends without rewriting applications.
Domain
Telecommunications / Open RAN / Generative AI
Deliverable
production ML models
Required skills
LLM architecture, RAG, retrieval-augmented generation, model evaluation, serving optimization, quantization, continuous batching, caching, parallelism, API design, security, data pipelines
Preferred skills
Multimodal models, workflow automation, tool permissions, observable production services
Responsibilities
Own the architecture and technical roadmap for a secure, reliable, and maintainable local LLM platform; Partner with engineering, product, support, IT, information security, legal, and domain experts to prioritize high-value use cases; Build a modular inference and model-gateway layer with stable APIs, model routing, streaming, concurrency controls, and the ability to change models or serving backends; Evaluate open-weight language, code, embedding, reranking, and, where useful, multimodal models against PW-specific tasks; Optimize serving across available CPU, GPU, and accelerator resources using techniques such as continuous batching, caching, parallelism, quantization, and right-sized context limits