Data Science AI Engineer Senior Professional

Summary

We are seeking a highly skilled and forward-thinking GenAI Engineer to join our AI innovation team. This role is ideal for someone with deep technical expertise in Generative AI, a strong foundation in Python programming, and a passion for driving enterprise AI transformation.

You will be instrumental in designing, developing, and deploying advanced Retrieval-Augmented Generation (RAG) systems. You’ll also play a pivotal role in enabling our internal workforce to embrace and adopt AI technologies.

We’re seeking a hands-on engineer to accelerate developer productivity and engineering quality by operationalizing GitHub Copilot (Business/Enterprise) across the SDLC, with a strong focus on secure, governed adoption. You will design and maintain Copilot customization assets (prompt files, custom instructions, reusable agents) for common .NET delivery workflows, and build supporting GenAI services on Azure where needed. You will partner with platform engineering, security, and product teams to define guardrails, measure impact (productivity, quality, and risk), and continuously improve developer experience.

Your role in our mission

GitHub Copilot Enablement & Productization

Own and evolve an enterprise-ready Copilot enablement approach: usage patterns, prompt standards, and governance for regulated environments.

Create and curate a repository-backed library of reusable prompt files (.github/prompts) for common engineering scenarios (bug fixes, brownfield enhancements from user stories, refactoring, Test generation, security remediation).

Author and maintain custom instruction files (repository and organization patterns) to enforce coding standards, architecture conventions, error handling, logging, and testing practices.

Design interactive ‘guided’ prompts that ask one question at a time, minimize friction for low adopters, and require user confirmation before applying code changes.

Collaborate with teams to integrate Copilot into day-to-day workflows in Visual Studio and GitHub (PR templates, checklists, review guidance).

Guardrails, Security & Quality

Define and implement guardrails so AI-assisted code can’t land without required quality and security signals (tests, reviews, and automated scanning).

Configure and enforce GitHub Advanced Security practices where applicable (CodeQL code scanning, dependency review/alerts, secret scanning/push protection) and integrate results into PR gating.

Establish measurement for AI-assisted development: Copilot usage metrics (suggested vs added LOC, acceptance actions) and repo outcomes (review cycle time, defect inflow proxies, security findings), with clear limitations and directional interpretation.

Partner with AppSec and compliance stakeholders to ensure safe handling of sensitive data in prompts, logs, and test artifacts.

• NET Engineering & Platform Integration Contribute to and review C#/.NET codebases (ASP.NET Core, EF Core) to ensure Copilot guidance and templates match real architecture and patterns. Build small, maintainable developer tooling and automation (e.g., GitHub Actions, internal utilities, code generators where appropriate) that complements Copilot rather than replacing engineering discipline. Create and maintain sample reference implementations and ‘golden paths’ that demonstrate secure patterns, test-first fixes, and high-quality PRs. GenAI Solution Engineering (Supporting) Develop LLM-powered workflows on Azure (Azure OpenAI) to support developer experience and engineering insights (e.g., PR summarization, guided debugging, quality dashboards). Implement prompt contracts, tool/function calling patterns, and evaluation harnesses for reliability, cost, and safety. Where needed, build retrieval-augmented generation (RAG) pipelines and connectors to enterprise knowledge sources with grounding/citations.
  
  

What Were Looking For

Must-Have

5–7 years of software engineering experience delivering production systems with strong engineering discipline (testing, reviews, CI/CD).

Hands-on experience using GitHub Copilot in professional development workflows; ability to design and operationalize prompt files, custom instructions, and reusable agent-like workflows for teams.

Practical experience with .NET (C#) and modern application development (ASP.NET Core and/or EF Core); able to read, debug, and implement changes confidently.

Strong GitHub fundamentals: branching strategies, PR-based delivery, code reviews, and GitHub Actions (or equivalent CI).

Security-minded engineering: familiarity with secure coding practices and integrating automated checks (SAST, dependency scanning, secret detection) into the delivery pipeline.

Azure fundamentals for deploying services (App Service/Functions/Container Apps) and secure configuration (Key Vault, RBAC).

Ability to convert moderately detailed requirements into clear designs (ADRs/sequence diagrams) and production-ready implementations.

Nice-to-Have

GitHub Copilot administration experience (policy management, organizational customization, adoption measurement and reporting).

Experience building developer tooling or IDE extensions (Visual Studio/VS Code), internal CLIs, or PR automation.

Hands-on with GitHub Advanced Security (CodeQL, secret scanning, dependency review/Dependabot) and rulesets/required checks for merge gating.

Experience with Azure OpenAI, prompt evaluation, and/or RAG (Azure AI Search or equivalent).

Data engineering and analytics experience for telemetry pipelines and dashboards (SQL, data modeling, Power BI).

Core Competencies

Developer Productivity Leadership: pragmatic enablement, playbooks, and training that drive real adoption.

System Design: clear, scalable architecture with documented trade-offs.

Code Quality: readable, tested, maintainable code with robust error handling.

Security & Governance: secure-by-default patterns, auditability, and responsible AI practices.

Measurement & Insights: metrics that are transparent, repeatable, and grounded in tooling constraints.

What You Should Expect In This Role

Copilot customization assets (prompts/instructions/workflows) that materially improve cycle time and developer experience without compromising quality or security.

Clear, trustworthy reporting of Copilot adoption and impact, including known limitations of telemetry and measurement.

Reduced friction for common work (small fixes, bug triage, test creation) through repeatable Copilot-guided workflows that keep developers in control.

Well-governed, secure AI-assisted development practices aligned with enterprise standards.

---