Semantic Search & Retrieval Engineering Lead

Role Overview: As a Principal Engineer at CIBC India, you will be responsible for designing and delivering the RAG Services Layer at the core of the AI platform. Your role will involve integrating various data types, developing ingestion pipelines, retrieval APIs, and ensuring the robustness and precision of retrieval services. You will play a crucial part in enhancing the bank's capabilities and supporting agents and applications across the organization.

Key Responsibilities: - Build and maintain the RAG Services Layer, including indexing, hybrid search, embedding pipelines, reranking, context assembly, and retrieval - Develop a semantic layer for various data domains such as Risk, PnL, trades, RFQ, limits, clients, and market - Implement hybrid retrieval strategies, metadata search, and entity-linked retrieval - Design structured-output schemas for agents retrieving tabular/financial data - Develop evaluation pipelines to measure precision, recall, and retrieval quality - Build real-time or near-real-time data flows for risk and PnL use-cases

Qualifications Required: - 12+ years of experience in Python engineering with a focus on RAG architectures, embedding pipelines, and hybrid search - Deep understanding of semantic modelling, metadata systems, and semantic layers - Experience with vector databases, API service development, and capital-markets datasets - Knowledge of Databricks, Delta Lake, and high-volume data ingestion - Familiarity with knowledge graph technologies and model fine-tuning/domain-adapted embeddings

(Note: Any additional details about the company have been omitted from the Job Description provided) Role Overview: As a Principal Engineer at CIBC India, you will be responsible for designing and delivering the RAG Services Layer at the core of the AI platform. Your role will involve integrating various data types, developing ingestion pipelines, retrieval APIs, and ensuring the robustness and precision of retrieval services. You will play a crucial part in enhancing the bank's capabilities and supporting agents and applications across the organization.

Key Responsibilities: - Build and maintain the RAG Services Layer, including indexing, hybrid search, embedding pipelines, reranking, context assembly, and retrieval - Develop a semantic layer for various data domains such as Risk, PnL, trades, RFQ, limits, clients, and market - Implement hybrid retrieval strategies, metadata search, and entity-linked retrieval - Design structured-output schemas for agents retrieving tabular/financial data - Develop evaluation pipelines to measure precision, recall, and retrieval quality - Build real-time or near-real-time data flows for risk and PnL use-cases

Qualifications Required: - 12+ years of experience in Python engineering with a focus on RAG architectures, embedding pipelines, and hybrid search - Deep understanding of semantic modelling, metadata systems, and semantic layers - Experience with vector databases, API service development, and capital-markets datasets - Knowledge of Databricks, Delta Lake, and high-volume data ingestion - Familiarity with knowledge graph technologies and model fine-tuning/domain-adapted embeddings

(Note: Any additional details about the company have been omitted from the Job Description provided)