Back
Strong employer brand and mid-level title increase competition, but niche LLM/vector DB skills moderate applicant density.
Requires specialized LLM, vector DB, and production ML experience, making backgrounds less transferable across unrelated domains.
Explicit 4+ years requirement plus many mandatory LLM, vector DB, and production tooling requirements enforce strict filtering.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own the design, operation, and scaling of a multi-tenant vector database and embedding pipelines for incident root cause analysis serving 100+ enterprise customers.
Build and tune retrieval layers, confidence scoring frameworks, and prompt systems that integrate multiple data types to generate actionable root cause analyses with automated routing.
Maintain quality assurance including test sets, calibration checks, prompt versioning, and monitoring of retrieval metrics and operational costs.
4+ years experience in AI/ML engineering, data engineering, NLP, or related field with hands-on LLM work.
Production experience with vector databases such as pgvector, Pinecone, or Weaviate.
Strong Python programming skills including FastAPI, Pydantic, SQLAlchemy, and asynchronous programming.
Experience building and operating large-scale data ingestion pipelines (e.g., Celery, Airflow).
Technical operator familiar with multi-tenant architectures requiring strict data isolation and production reliability.
Experienced in designing and validating prompt engineering and LLM output schemas for structured, automated decision systems.
Skilled in embedding models, semantic search, retrieval-augmented generation (RAG), and calibration techniques for confidence scoring in AI-driven pipelines.