Senior/Principal Language Model Engineer
Kfar Saba • Full Time
Posted 3mo ago
Job Location
Kfar Saba
Tech Stack
Remote Work Policy
On-site
Employment Type
Full Time
Categories
LLM Engineer
About the job
Parallel Wireless is seeking a hands-on technical leader to build and operate a secure local large-language-model (LLM) platform. This platform will enable engineering and business teams to leverage generative AI with proprietary data, including source code, product documentation, and technical standards, while ensuring sensitive information remains within company-controlled environments. This senior individual contributor role involves applied LLM engineering, platform architecture, data pipelines, security, and production operations. The goal is to transform promising prototypes into a dependable internal capability by selecting and optimizing open-weight models, building permission-aware retrieval, creating reusable APIs and tools, and establishing metrics for quality, safety, and business value. The role emphasizes a holistic approach to enterprise LLMs, requiring trustworthy source grounding, strong access controls, repeatable evaluation, observable production services, and a robust operating model for managing data, indexes, prompts, and models.
Responsibilities
- Own the architecture and technical roadmap for a secure, reliable, and maintainable local LLM platform.
- Partner with various teams to prioritize use cases and translate them into platform requirements.
- Build a modular inference and model-gateway layer with stable APIs and robust controls.
- Evaluate and document open-weight language, code, embedding, and multimodal models.
- Optimize model serving across available hardware resources using advanced techniques.
- Design and operate RAG and enterprise-search pipelines for various data sources.
- Enforce source-system permissions throughout ingestion and retrieval.
- Establish evaluation datasets and automated testing for retrieval quality and accuracy.
- Create release gates and reproducible regression tests for platform changes.
- Implement end-to-end observability for model and agent workflows.
- Design safe tool-calling and agent workflows with least-privilege access.
- Integrate the platform into existing employee tools through SDKs and APIs.
- Build operational foundations for production use, including CI/CD, registries, and disaster recovery.
- Protect proprietary and personal information through security measures and risk defenses.
- Determine when prompt or retrieval improvements are sufficient versus when model adaptation is justified.
- Make the platform usable beyond the core AI team through documentation and training.
Requirements
- Hands-on technical leadership experience.
- Experience building and operating secure local LLM platforms.
- Expertise in applied LLM engineering, platform architecture, search, data pipelines, security, and production operations.
- Ability to select and optimize open-weight models.
- Experience building permission-aware retrieval systems.
- Proficiency in creating reusable APIs and tools.
- Experience integrating with existing engineering workflows.
- Ability to establish objective measures for quality, safety, latency, capacity, and business value.
- Understanding of enterprise LLM requirements including source grounding, access controls, evaluation, and operating models.
- Pragmatic decision-making on build-versus-buy and choosing the simplest effective approach (search, RAG, prompting, workflow automation, model adaptation).
- Experience with enterprise search, retrieval-augmented generation (RAG), and prompt engineering.
- Familiarity with model provenance, licenses, security posture, hardware needs, and total cost of ownership.
- Experience optimizing model serving across CPU, GPU, and accelerators.
- Knowledge of techniques like continuous batching, caching, parallelism, and quantization.
- Experience designing and operating RAG and enterprise-search pipelines.
- Expertise in parsing, chunking, metadata, embeddings, hybrid retrieval, reranking, and freshness.
- Experience enforcing source-system permissions and integrating with identity management systems (SSO, RBAC).
- Experience establishing versioned evaluation datasets and automated testing.
- Experience creating release gates, reproducible regression tests, and supporting canary releases.
- Proficiency in implementing end-to-end observability for model and agent workflows.
- Experience designing safe tool-calling and agent workflows.
- Experience integrating platforms into developer environments, source control, CI workflows, and knowledge systems.
- Experience building operational foundations like CI/CD, configuration registries, backups, and disaster recovery.
- Knowledge of network isolation, encryption, retention controls, and defenses against prompt injection and data poisoning.
- Experience with parameter-efficient fine-tuning, distillation, or other model adaptation techniques.
- Ability to create documentation, examples, and training for end-users.