Senior/Principal Local LLM & Generative AI Platform Engineer

Parallel Wireless

Remote regions

US

Benefits

Similar Jobs

See all

Platform Architecture:

  • Own the end-to-end architecture for a secure, modular local LLM platform with model gateways, RAG pipelines, and permission-aware retrieval.
  • Build reusable APIs and SDKs that integrate with existing engineering workflows and tools.

Model Evaluation & Optimization:

  • Evaluate open-weight models against company-specific tasks and optimize serving across CPU/GPU resources with quantization and caching.
  • Establish automated evaluation pipelines for retrieval quality, factual accuracy, latency, and safety.

Production Operations:

  • Deploy and operate containerized services on Kubernetes with CI/CD, observability, and incident response.
  • Implement least-privilege tool-calling, input/output validation, and protections against prompt injection and data leakage.

Parallel Wireless

Parallel Wireless is a U.S.-based pioneer in Open RAN innovation, transforming how mobile networks are built and powered. The company is a leader in software-centric, hardware-agnostic network solutions with a focus on reducing complexity and total cost of ownership.

Apply for This Position