– SDLC GenAI Automation & Tooling Integrations Engineer

M&T Bank•Buffalo, NY

1d•$116,400 - $194,000•Onsite

About The Position

SDLC GenAI Automation & Tooling Integrations Engineer will play a key role in automating and modernizing the enterprise SDLC by designing, building, integrating, and enhancing GenAI-enabled tooling and engineering capabilities. This role will partner closely with the SDLC Program Governance Lead, SDLC BSAs, GenAI engineering stakeholders, internal SDLC tool owners, and Technology delivery teams to reduce manual SDLC effort, improve artifact quality, strengthen governance traceability, and embed controls where engineering work occurs. This engineer will help build and mature AI-driven workflows that support SDLC artifact creation, artifact validation, approval routing, metrics capture, governance reporting, and tool-based evidence generation. The role will require strong software engineering fundamentals, practical GenAI engineering experience, workflow orchestration skills, integration experience across enterprise tools, and the ability to maintain quality, security, and architectural oversight while leveraging AI models as primary execution engines. The role is expected to support the creation of SDLC metric dashboards and data pipelines that help measure SDLC governance, adoption, compliance, control effectiveness, process efficiency, and improvement opportunities. The engineer will also help ensure GenAI-generated outputs meet SDLC quality standards through context engineering, prompt/policy design, agent workflow design, validation routines, human-in-the-loop controls, and repeatable quality gates.

Requirements

Associate’s degree and a minimum of 7 years’ systems analysis and/or application development work experience or Bachelor's degree and a minimum of 5 years' systems analysis and/or application development work experience. In lieu of a degree, a combined minimum of 9 year’s education and/or relevant work experience, including a minimum of 5 years’ system analysis and/or application development work experience.
Strong foundation in software architecture, system design, API design, integration patterns, engineering best practices, secure coding, testing, CI/CD, and operational support.
Demonstrated experience designing, building, testing, and iterating software solutions rapidly using modern development practices and AI-assisted development workflows.
Hands-on experience using GenAI models, coding assistants, prompt engineering, RAG/context engineering, model evaluation, or agent-based automation to support software delivery outcomes.
Demonstrated ability to orchestrate workflows across multiple AI models and tools, leveraging model-specific strengths for optimal output quality, speed, and reliability.
Experience designing and implementing multi-step AI-driven automation or agent-based workflows with human review, validation, monitoring, and exception handling.
Expertise in AI-assisted debugging, including structured prompts, multi-model validation, root-cause analysis, systematic edge-case identification, vulnerability analysis, and output verification.
Experience integrating enterprise tools through APIs, webhooks, pipelines, service accounts, event-driven patterns, or middleware.
Experience with SDLC, Agile delivery, DevOps, testing, change/release management, source control, artifact management, and production readiness practices.
Strong communication, collaboration, problem-solving, documentation, and stakeholder engagement skills.

Nice To Haves

Experience with GitLab Duo, GitLab, GitLab pipelines, Jira, Zephyr, ServiceNow, Confluence, SharePoint, SonarQube, Artifactory, Power BI, Azure AI Foundry, Copilot Studio, or similar tools.
Experience building dashboards, data pipelines, telemetry, analytics, or governance reporting solutions for technology delivery, compliance, controls, DevOps, or SDLC programs.
Experience developing agent-based workflows, tool-using agents, AI orchestration layers, prompt/template registries, model routing, evaluation harnesses, or AI control/observability patterns.
Experience with Azure, Kubernetes, Terraform, Key Vault, managed identities, observability platforms, API gateways, CI/CD runners, secrets management, or enterprise cloud engineering.
Certifications or demonstrated training in cloud engineering, software architecture, AI engineering, DevOps, ITIL, or related disciplines.

Responsibilities

Build and enhance GenAI tooling and agent-based capabilities that automate SDLC work while preserving governance, traceability, quality, and control.
Design integrations across SDLC tool ecosystems, including GitLab Duo, GitLab, Jira, Zephyr, ServiceNow, Confluence, SharePoint, SonarQube, Power BI, and related engineering platforms.
Automate SDLC artifact generation and validation, including requirements, acceptance criteria, test planning artifacts, traceability outputs, permit readiness artifacts, evidence packages, workflow summaries, release notes, and governance dashboards.
Engineer AI context-setting, prompt templates, model routing, agent workflows, validation patterns, and quality gates to ensure generated artifacts meet SDLC standards.
Support SDLC metric dashboards, telemetry, data pipelines, and reporting automation needed for governance, adoption, compliance, control effectiveness, and process improvement insights.
Rapidly prototype, test, and iterate on AI-driven development workflows while maintaining architecture, security, observability, and operational-readiness discipline.
Design, build, test, and maintain GenAI-enabled capabilities that automate SDLC activities such as requirements decomposition, design validation, testing support, evidence generation, SDLC adherence measurement, workflow summarization, and governance reporting.
Develop agent-based workflows that use AI models to generate, validate, refine, and route SDLC artifacts while preserving required human review, approval, and audit evidence.
Create reusable engineering patterns for context injection, prompt templates, grounding data, artifact validation, model evaluation, confidence scoring, and output quality controls.
Leverage AI models as primary execution engines while maintaining architectural, quality, security, and operational oversight of generated outputs and automated actions.
Design fail-safe and human-in-the-loop patterns for AI-assisted SDLC automation, especially where generated artifacts, workflow actions, approvals, or downstream publishing may affect compliance or delivery outcomes.
Partner with internal tool owners for GitLab Duo, GitLab, Jira, Zephyr, ServiceNow, Confluence, SharePoint, SonarQube, Power BI, and related platforms to design and build integrations that support SDLC automation.
Design and implement integrations for SDLC artifact creation, artifact publishing, test artifact generation, approval routing, evidence capture, dashboard reporting, workflow status synchronization, and traceability across tools.
Build APIs, services, connectors, pipeline jobs, automation scripts, event-driven workflows, and data transformations needed to connect SDLC systems of record and supporting tooling.
Support integration patterns that connect requirements, Jira work items, generated artifacts, test cases, Zephyr evidence, GitLab repositories, merge requests, ServiceNow permits/RFCs, and dashboard metrics.
Engineer AI context-setting patterns so generated SDLC artifacts are grounded in approved standards, procedures, templates, examples, decision logic, and quality criteria.
Build agent workflows that can identify incomplete context, generate clarification questions, detect artifact gaps, flag low-quality outputs, and route items for human review when needed.
Lead the creation of SDLC metric dashboards by building data pipelines, data models, telemetry capture, reporting views, automated extracts, and integration points across SDLC tools.
Help automate collection of metrics related to SDLC adoption, workflow usage, permit applicability, artifact completion, approval cycle times, evidence quality, test coverage, defect leakage, control adherence, and process efficiency.
Build operational dashboards and support dashboards that make SDLC automation health, integration health, workflow throughput, defects, incidents, latency, and user adoption visible.
Use AI-assisted debugging techniques to identify root causes, validate assumptions, compare alternative solutions, and accelerate defect resolution while maintaining engineering judgment and accountability.
Apply strong software architecture, system design, and engineering best practices to evaluate, refine, and operationalize AI-generated and human-authored solutions.
Partner with Enterprise Architecture, Cybersecurity, Risk, AI governance, tool owners, and platform teams to ensure GenAI automation patterns align with approved architecture, security, data, and governance expectations.
Provide technical support and troubleshooting for SDLC automation capabilities, dashboards, integrations, AI-agent workflows, and artifact-generation tools.
Create technical documentation, integration guides, runbooks, support notes, examples, and engineering patterns that enable maintainability and adoption.
Participate in backlog refinement, solution design, demos, pilot support, office hours, feedback review, and continuous improvement routines.