SQM Infrastructure Product Development AI Engineer

Description

The company is a global wealth management, asset servicing, asset management and banking firm listed on Nasdaq as NTRS. It serves wealthy individuals, families, corporations and institutions.

Founded in 1889, it has more than 135 years of financial experience and over 24,000 staff, whom it calls partners.

This is a hands-on AI Engineer role focused on product development and building enterprise Generative AI solutions.

You will work through the whole product life cycle, from architecture and prototypes to API development, deployment, evaluation, monitoring and production support.

The team wants someone who knows LLMs, RAG, agentic AI, Python, Azure and cloud-native engineering, and who thinks like a product builder with a focus on scalability, reliability, security and user experience.

The company offers a flexible, collaborative culture with strong financial stability, encourages internal moves, makes senior leaders accessible and supports the communities it serves.

Responsibilities

• Build enterprise agentic AI and Generative AI apps with LangChain/LangSmith and LangGraph.
• Assemble multi-step, stateful workflows that combine reasoning, tool calls, retrieval and human-in-the-loop steps.
• Set up retrieval-augmented generation pipelines on PostgreSQL with pgvector for vector storage and semantic search.
• Connect applications to Azure OpenAI and other LLM services.
• Craft prompts and reusable prompt templates using advanced prompt engineering methods.
• Write scalable backend services and REST APIs in Python with FastAPI.
• Create tooling that measures answer quality, latency, reliability and retrieval accuracy.
• Trace, evaluate, debug and monitor LLM and agent workflows in LangSmith.
• Package AI services in containers and deploy them to Azure Kubernetes Service (AKS).
• Choose suitable Azure services for identity, security, networking, storage, monitoring and application integration.
• Put production practices in place, including error handling, logging, retries, API security, configuration management and observability.
• Work with product owners, architects and engineers to turn business needs into scalable AI features.
• Take part in design and code reviews, testing, deployment, troubleshooting and ongoing product improvements.
• Test new LLM, retrieval and agent techniques and adopt those that add measurable product value.
• During major incidents and production issues, work with application, infrastructure, cloud, database and operations teams to find dependencies and fix problems.

Requirements

• You have worked with LLMs, Azure OpenAI, retrieval-augmented generation, prompt engineering, and agentic AI or AI agents.
• You know LangChain, LangGraph and LangSmith, and you have evaluated and monitored LLM output quality.
• You build applications in Python and FastAPI, including REST APIs, async APIs and microservices.
• You have used PostgreSQL and pgvector, vector embeddings, semantic search, and RAG indexing and retrieval patterns.
• You have deployed to Microsoft Azure, including AKS, using Docker containers, cloud-native design and CI/CD with production deployment practices.
• You have taken AI capabilities beyond proof of concept into production, including translating business requirements into technical capabilities, designing reusable AI architectures, and balancing quality, latency, cost, security and scalability.
• You have designed APIs and integration patterns for enterprise applications, set AI evaluation and quality measures, and troubleshot production LLM and RAG applications.
• You have worked across engineering, architecture, product, QA, DevOps and business teams, and owned features from design through deployment and production stabilization.
• Preferred: hands-on experience building enterprise GenAI or RAG products.
• Preferred: experience building LangGraph-based agentic workflows.
• Preferred: hands-on experience with LangSmith tracing and evaluation.
• Preferred: experience deploying Python/FastAPI applications on AKS.
• Preferred: experience with PostgreSQL and pgvector at production scale.
• Preferred: understanding of LLM hallucination, grounding, context management, guardrails and evaluation.
• Preferred: familiarity with Azure identity, secrets management, monitoring and enterprise security patterns.
• Plus: experience building internal developer, infrastructure, automation, operations or knowledge-management AI products.

Conditions

The base salary range is $80,800 - 133,400 USD. This range is a good faith estimate of base pay.

You must be authorized to work in the U.S. without employment-based visa sponsorship, now or in the future. The company will not sponsor U.S. work visas for this role, including H-1B, L-1, TN, O-1, E-3, H-1B1, F-1, J-1, OPT, CPT or any other employment-based visa.

Benefits

• Retirement benefits, including a 401k and a pension.
• Health and welfare benefits: medical, dental, vision, spending accounts and disability cover.
• Paid time off, parental and caregiver leave, life and accident insurance, and other voluntary and well-being benefits.
• A discretionary bonus program that may include an equity component.
• Philanthropy is central to the culture, and employees give time and talent to their communities worldwide.