Description

You will architect and build identity resolution systems and LLM-powered applications to establish the authoritative customer identity graph.

Responsibilities

• Design end-to-end identity resolution architecture using probabilistic models, ML, and embedding-based techniques for billions of records.
• Architect candidate generation and blocking strategies, including LSH and semantic similarity, to balance precision with computational feasibility.
• Build LLM-powered systems for entity resolution, implementing zero-shot/few-shot classification and RAG-based architectures for data enrichment.
• Develop NLQ-to-SQL platforms enabling business users to query the CDP using natural language with schema awareness and guardrails.
• Optimize vector search architectures using transformer models and ANN systems for large-scale retrieval and semantic identity matching.

Required Skills

• 6+ years of experience in ML/AI engineering.
• Bachelor's degree in Computer Science or related field.
• Advanced programming in Python with strong SQL skills.
• Distributed data processing with Spark and Dask.
• Proven experience building production-grade entity resolution or identity graph systems at scale.
• Deep expertise in ML algorithms for similarity, classification, and clustering.
• Hands-on experience with transformer models, embeddings, and semantic search at population scale.
• Experience with LLM APIs and orchestration frameworks like LangChain or LangGraph.
• Expertise in vector databases such as Pinecone, Qdrant, pgvector, or FAISS.

Preferred Skills

• Expertise in ML lifecycle management using MLflow.
• Understanding of data governance, privacy, and security requirements.

Key Skills

Education

Bachelor's degree