AI Solutions Engineer

Vantage Bank • Fort Worth, TX

23h

About The Position

The AI Solutions Engineer designs, builds, deploys, and supports production AI systems for Vantage Bank. The role develops agentic workflows, retrieval pipelines, tool-calling integrations, and evaluation frameworks that demonstrate correct and controlled behavior. Given a scoped problem and defined outcome, the engineer independently determines the technical approach, delivers a working solution, and raises design options and risks early. The position also provides technical leadership in support of the bank’s AI strategy, governance, and responsible adoption of AI technologies.

The engineer builds and evaluates AI solutions using bank documents and governed data; integrates systems with bank applications and services under least-privilege controls; and operates production services with versioning, approvals, monitoring, cost visibility, alerting, and incident follow-through. The role produces audit-ready documentation and lightweight internal applications, and supports AI enrichment pipelines and governed natural-language analytics. Solutions must comply with Vantage Bank’s AI strategy, policies, and guidelines.

Requirements

• Bachelor’s degree in Data Science, Computer Science, Information Systems, Statistics, Business Analytics, or a related quantitative field; equivalent applied experience may be considered.
• At least 4 years of experience building and delivering software or data systems, including at least 2 years of hands-on development of AI- or LLM-based solutions that reached users in a production or pre-production setting.
• Hands-on experience building agentic and tool-calling systems with frameworks such as LangGraph, LangChain, AutoGen, or Mosaic AI, including structured outputs, function calling, API or MCP integrations, end-to-end implementation, and behavioral control design.
• Ability to describe a specific agentic implementation end to end and explain the controls that constrained its behavior.
• Demonstrated expertise in RAG systems, including chunking trade-offs, embedding selection, hybrid retrieval, re-ranking, and evaluation frameworks covering benchmark datasets, hallucination and grounding detection, access-boundary and regression testing, judge calibration, and root-cause analysis distinguishing retrieval from generation failures.
• Strong Python and SQL proficiency, with end-to-end ownership of solution design, risk identification, and delivery, and the ability to debug, optimize, explain, and defend code regardless of development tools used.
• Practical understanding of Databricks AI/BI capabilities, Genie Spaces, and Unity Catalog business semantics and governed data access patterns, or comparable metadata and governance platforms.
• Working understanding of governed environments, including least-privilege access, audit logging, and change control.
• Ability to document solution logic, prompt instructions, verified queries, test cases, governance assumptions, limitations, and user-adoption guidance in an audit-ready format.
• Clear communication with non-technical colleagues, including the ability to explain system capabilities and limitations to people who will not read the code.
• Self-motivated, with strong initiative, a high level of accountability, and attention to detail.
• Ability to maintain high ethical standards and complete confidentiality.

Nice To Haves

• Production experience with Azure OpenAI, OpenAI, Anthropic, or comparable model APIs, including cost and latency management.
• Familiarity with AI Gateway or comparable LLM governance capabilities, such as approved-model routing, usage monitoring, audit logging, cost attribution, and rate limits.
• Experience with MLflow or a comparable experiment and model registry; continuous integration and delivery using Azure DevOps or GitHub; containerization; observability tooling; agile delivery practices; and lightweight application frameworks such as SQL AI Functions, Databricks Apps, Streamlit, or Gradio.
• Understanding of banking or financial-services data, including customer, deposit, lending, fraud, AML, compliance, or operational reporting domains.
• Exposure to responsible AI practices in financial services, including acceptable-use boundaries, model-risk awareness, explainability expectations, and audit-ready documentation.

Responsibilities

• Design and build multi-step agentic AI workflows with tool calling, controlled state transitions, defined boundaries, human review points, and sufficient logging to reconstruct decisions.
• Build and tune retrieval-augmented generation pipelines over bank documents and governed data, including chunking, embedding selection, hybrid and semantic retrieval, re-ranking, and separate evaluation of retrieval and answer quality.
• Integrate AI systems with bank data, applications, and services through tool-calling interfaces and Model Context Protocol servers and clients, using least-privilege access, auditable call logs, and read-only defaults for potentially write-capable functions.
• Build and operate evaluation tooling, including benchmark question sets, hallucination and grounding checks, user-identity access-boundary tests, prompt and model regression suites, and model-graded scoring calibrated against human labels.
• Build and maintain evaluation harnesses for the role’s solutions and shared bank-wide use, keeping them current as prompts, models, and requirements change.
• Deploy, monitor, and support production AI services, including prompt and model versioning, approval routing for higher-risk use cases, drift and quality monitoring, usage and cost visibility, alerting, and incident response with root-cause follow-through.
• Produce defensible documentation for AI solutions, including solution logic, prompt instructions, verified queries, test cases and results, governance assumptions, known limitations, and plain-language safe-use guidance.
• Build solutions in accordance with Vantage Bank’s AI strategy, policies, and guidelines, and contribute engineering perspectives to governance questions on assigned use cases.
• Stand up lightweight internal applications, such as Databricks Apps or Streamlit applications, for branch, lending, or operations teams.
• Build AI enrichment pipelines using SQL AI Functions or equivalent for summarization, classification, and structured extraction, and validate generated fields before downstream use.
• Support governed natural-language analytics on Genie Spaces, including semantic definitions, verified SQL examples, and Unity Catalog metadata, when required by agentic solutions.
• Perform other related duties as assigned.
• Complete required BSA training and comply with the Bank Secrecy Act, Anti-Money Laundering, and Office of Foreign Asset Control Policy.
• Embrace Vantage Bank’s community involvement and culture, including teamwork, service, and opportunities to give back.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level