Principal AI Systems & LLM Architect
Join the engineering team building hardened digital infrastructure, zero-trust cryptographic platforms, and high-velocity developer tools.
Role Overview
Architect scalable agentic AI workflows, high-precision retrieval-augmented generation (RAG) engines, and enterprise AI safety guardrails. Bridge foundational models with high-performance vector stores, real-time embeddings, and deterministic tool-calling runtimes.
Key Requirements & Qualifications
- ✓ 10+ years of total software engineering with at least 4+ years specializing in deep learning, NLP, and production LLM orchestration.
- ✓ Demonstrated experience designing high-accuracy RAG architectures with hybrid search (dense embeddings + BM25/sparse), re-ranking, and semantic routing.
- ✓ Hands-on mastery of vector databases (Qdrant, Pinecone, pgvector) and distributed model serving (vLLM, TensorRT-LLM).
- ✓ Expertise in agentic execution frameworks, stateful graph engines (LangGraph, custom orchestrators), and strict latency/cost optimization.
- ✓ Deep commitment to AI security, jailbreak mitigation, prompt-injection defense, and verifiable LLM outputs.
Why Build With EyesOn SafeTech
No micromanagement or endless status meetings. High trust with direct production ownership.
Solve difficult real-world engineering problems across cryptography, PKCS#11, and microservices.
Asynchronous communication, flexible work hours, and autonomy engineered from day one.
Competitive salary benchmarks, hardware stipends, and performance incentives.
Submit Your Application
Upload your resume to auto-fill details, or fill the form manually.
We extracted your details below. You can review and edit before submitting.
Application Received
Thank you for applying for Principal AI Systems & LLM Architect. Your application and resume have been delivered directly to our hiring team. We review all applications within 48 hours.