Back
Tier-1 brand, mid-level generalist title, and Bangalore location increase applicant density despite niche LLM requirements.
Highly specialized LLM, vector DB, and RAG production experience limits cross-industry transferability.
Explicit 4+ years, mandatory vector DB/LLM production experience, and specific Python/stack requirements tighten filters.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own design and operation of a multi-tenant pgvector database for root cause analysis, including indexing, query tuning, and strict tenant data isolation.
Build and maintain embedding pipelines and retrieval layers (RAG) for operational documents, optimizing relevance and scoring for automatic vs. human incident notifications.
Develop and maintain confidence scoring frameworks, prompt engineering for LLM reasoning (Claude API), and evaluation systems with golden test sets to ensure RCA accuracy and performance.
Minimum 4 years experience in AI/ML engineering, data engineering, NLP, or closely related field with hands-on LLM experience.
Production experience building and operating vector databases such as pgvector, Pinecone, or Weaviate.
Strong Python skills including FastAPI, Pydantic, SQLAlchemy, and async programming.
Experience designing, deploying, and operating scalable data ingestion pipelines (e.g., Celery, Airflow).
Expertise in prompt engineering for production LLM systems requiring reliable structured outputs and LLM evaluation frameworks with golden test sets.
Experience working with multi-tenant architectures enforcing strict data isolation and practical knowledge of semantic search techniques (cosine similarity, ANN, hybrid search).
Operational focus on continuous calibration, monitoring, and tuning of AI/ML systems involving confidence scoring, retrieval quality metrics, and cost/latency management.