Associate, AI Engineer - Pune - Multiple roles

About Northern Trust As a global leader in innovative wealth management, asset servicing, asset management and banking services, Northern Trust (Nasdaq: NTRS) is proud to guide the world’s most successful individuals, families, corporations and institutions. Since 1889, we have aligned our efforts with our three guiding Principles That Endure: Service, Expertise, and Integrity. Together, they reflect the three cornerstones of business conduct which we strive to instill in our employees, whom we call partners, and to provide to our clients and the communities we serve worldwide. With more than 135 years of financial experience and over 24,000 partners, we serve the world’s most sophisticated clients using leading technology and exceptional service. Job Summary: Early-career Full Stack Engineer with a focus on AI Engineering to help build next-generation intelligent applications powered by large language models (LLMs). This role sits at the intersection of application development, data engineering, and applied AI—developing scalable systems that leverage RAG (Retrieval-Augmented Generation), LLM evaluation frameworks, and agent-based architectures. You will work closely with platform, data, and product teams to build AI-powered experiences using Azure, Databricks, Postgres, and modern AI/agent frameworks. Major Duties: AI & Application Development  Build end-to-end AI-powered applications (UI + backend services + model orchestration)  Design and implement RAG pipelines for enterprise knowledge retrieval and grounding  Develop and deploy LLM-based workflows and agents (multi-step reasoning, tool use, orchestration)  Integrate models via APIs and hosted platforms (Databricks, Azure AI Foundry, etc.)  LLM Evaluation & Quality  Develop LLM evaluation frameworks (accuracy, hallucination detection, relevance, safety)  Implement automated testing and benchmarking for prompt chains and agents  Define and monitor LLM performance metrics (precision, recall, grounding fidelity)  Support experimentation (prompt engineering, model comparisons, fine-tuning readiness)  Data & Backend Engineering  Build and optimize data pipelines leveraging Databricks (Spark, Delta)  Design and query structured and semi-structured datasets using Postgres  Enable efficient retrieval layers (vector search, embeddings, indexing strategies)  Support data modeling for AI use cases (knowledge bases, feature stores)  Platform & Agent Development  Develop AI agents within Databricks and Azure ecosystems  Integrate orchestration frameworks (LangChain, LangGraph, AutoGen, or similar)  Build reusable services/APIs for agent capabilities (search, summarization, reasoning)  Full Stack Development  Contribute to lightweight front-end interfaces for AI applications (React or similar)  Build backend APIs/services (Python-based frameworks)  Ensure production readiness (logging, monitoring, scalability, security)  Experience & Qualification: