Associate AI Engineer
About The Position
Northern Trust is seeking an Associate AI Engineer to build end-to-end AI-powered applications. This role involves designing and implementing RAG pipelines, developing and deploying LLM-based workflows and agents, and integrating models via APIs and hosted platforms. The engineer will also be responsible for developing LLM evaluation frameworks, implementing automated testing, and defining LLM performance metrics. Additionally, the role includes building and optimizing data pipelines, designing and querying datasets, and enabling efficient retrieval layers. The engineer will also develop AI agents within Databricks and Azure ecosystems, integrate orchestration frameworks, and build reusable services/APIs. Contribution to lightweight front-end interfaces and backend APIs/services is also expected, ensuring production readiness.
Requirements
- Applicants must be authorized to work in the U.S. without the need for employment-based visa sponsorship now or in the future.
- Northern Trust will not sponsor applicants for U.S. work visa status for this opportunity (no sponsorship is available for H-1B, L-1, TN, O-1, E-3, H-1B1, F-1, J-1, OPT, CPT or any other employment-based visa).
Nice To Haves
- React or similar for front-end interfaces
- Python-based frameworks for backend APIs/services
- Databricks (Spark, Delta) for data pipelines
- Postgres for structured and semi-structured datasets
- LangChain, LangGraph, AutoGen, or similar orchestration frameworks
- Databricks and Azure ecosystems for AI agents
- Azure AI Foundry for model integration
Responsibilities
- 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.)
- 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)
- 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)
- 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)
- 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)
Benefits
- retirement benefits (401k and pension)
- health and welfare benefits (medical, dental, vision, spending accounts and disability)
- paid time off
- parental and caregiver leave
- life & accident insurance
- other voluntary and well-being benefits
- discretionary bonus program that may include an equity component
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Entry Level
Education Level
No Education Listed
