GenAI Observability & Governance Engineer | On-Prem OpenShift

Bank of America

Plano (TX)

On-site

USD 103,000 - 180,000

Full time

9 days ago

Application generator

An application made for this job — a tailored resume and cover letter that speak straight to the posting.

Get past ATS filters

Job summary

Bank of America in Plano, TX is seeking a senior software engineer to build and operate on-prem OpenShift-based GenAI monitoring and governance tools. You will deploy containerized services and integrate guardrails with enterprise GenAI applications.

The role requires 10+ years in software engineering, strong Python, OpenShift/Kubernetes, and experience with LLM/RAG platforms. You will collaborate across teams, lead engineering standards, and help advance governance initiatives.

Qualifications

Bachelor's or Master's degree in Computer Science, Data Science, MIS, related field, or equivalent experience.
10+ years of software engineering experience designing, building, and scaling production applications.
Strong Python development experience, including data and machine learning libraries.
Experience deploying and supporting containerized workloads on OpenShift or Kubernetes.
Experience taking LLM or RAG-based applications into production.
Understanding of AI risks, agent behavior, and governance frameworks.
Experience building APIs and integrating third-party platforms.
Experience with OpenAI APIs and orchestration frameworks such as LangChain.
Understanding of inference performance optimization and observability.
Experience implementing AI guardrails and model-based evaluation frameworks.
Experience working in Agile environments.
Demonstrated technical leadership and stakeholder influence.

Responsibilities

Develop, deploy, and support vendor applications in a fully on-premises OpenShift environment.
Build APIs and integrations connecting guardrail and observability tools with enterprise GenAI applications.
Implement and maintain operational monitoring for application performance, safety, latency, and quality metrics.
Develop and calibrate model-based evaluation workflows including annotation and feedback processes.
Utilize orchestration frameworks such as LangChain for guardrails, prompt management, and scoring workflows.
Create observability dashboards and alerting capabilities.
Troubleshoot production issues and improve scalability, reliability, and performance.
Support emerging agentic and multi-step AI workflows.
Lead and mentor team members while driving engineering standards and cross-functional delivery.