Back
Strong brand, metro location, mid-level generalist title, and 3–6 year target increase candidate competition.
Specialized LLM, vector DB, and multitenant production requirements create strong domain bias.
Multiple mandatory LLM, vector DB, and production engineering skills plus explicit 4+ years make filtering strict.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own and operate the full AI pipeline for root cause analysis across 100+ enterprise tenants, including vector database design, embedding pipelines, and retrieval systems.
Design and maintain the confidence scoring framework and routing logic for automated vs human incident notifications, ensuring accuracy and calibrated output.
Continuously evaluate and improve system performance with test sets, calibration checks, version control, and monitoring of cost, latency, and retrieval quality metrics.
4+ years of experience in AI/ML engineering, data engineering, NLP, or closely related fields with hands-on LLM experience.
Production experience building and operating vector databases (e.g., pgvector, Pinecone, Weaviate).
Proficient in Python, including FastAPI, Pydantic, SQLAlchemy, and asynchronous programming.
Experience designing and operating large-scale data ingestion pipelines (e.g., Celery, Airflow).
Experience with prompt engineering and building reliable structured outputs for production LLM systems beyond demos or chatbots.
Demonstrated ability to build and run LLM evaluation frameworks using golden test sets and accuracy metrics.
Familiarity with RAG retrieval systems, multi-tenant architectures requiring strict data isolation, and confidence calibration techniques.