Role Overview-

Product Engineering

- Design, develop, and maintain features across the product's codebase, primarily using C# and the .NET (Core/Framework) stack, following engineering best practices and architectural standards.

- Build and maintain CI/CD pipelines, work item tracking, and release processes using Azure DevOps (Pipelines, Repos, Boards, Artifacts).

- Participate in the full SDLC: requirements refinement, technical design, implementation, testing, code review, deployment, and post-release support.

- Collaborate with product managers, designers, and other engineers to translate requirements into working, well-tested software.

- Own the quality, performance, and maintainability of the code and systems you build.

AI-Accelerated Development

- Evaluate, adopt, and champion AI-assisted development tools (e.g., AI coding assistants, code-generation copilots, AI-powered code review and testing tools) to speed up day-to-day engineering work.

- Build and refine prompt patterns, reusable templates, and internal workflows that let the team use AI tools consistently and effectively across the SDLC.

- Apply AI tools to accelerate specific SDLC stages, including: requirements analysis and user story generation, technical design and architecture exploration, code generation and refactoring, automated test-case generation and test coverage improvement, automated code review and static analysis, documentation generation, and release-note/changelog automation.

- Identify opportunities to integrate AI capabilities directly into internal tooling and Azure DevOps CI/CD pipelines (e.g., AI-assisted PR review in Azure Repos, automated regression-test generation, AI-augmented Azure Pipelines gates, anomaly detection in build/deploy pipelines).





- Stay current with the fast-moving AI tooling landscape and proactively bring in new tools, models, or techniques that could improve team velocity or code quality.

- Balance AI-driven speed with responsible engineering practice ensuring AI-generated code and content is reviewed, tested, secure, and meets the team's quality bar before it ships.

Quality, Efficiency & Continuous Improvement

- Help define and track metrics that demonstrate the impact of AI-tool adoption on the SDLC (e.g., cycle time, defect rate, PR review time, test coverage, deployment frequency).

- Contribute to internal playbooks, guidelines, and training so the wider engineering team can adopt effective AI-assisted workflows.

- Continuously look for bottlenecks in the development process and propose AI-enabled or process-based solutions to remove them.

Forward Deployed Engineering

- Work directly with customers to understand workflows, pain points, and operational constraints, translating ambiguous business needs into practical technical solutions.

- Own customer-facing deployments from discovery and pilot through production rollout, including configuration, integration, troubleshooting, and adoption support.

- Capture field learnings and recurring customer requirements, feeding them back into product and engineering teams to improve reusable platform capabilities.





Required Skills & Experience

- Strong hands-on software engineering experience in C# and the .NET ecosystem (.NET Core / .NET Framework), including building and maintaining production-grade applications and/or APIs (e.g., ASP.NET Core, Web API, Entity Framework).

- Solid working experience with Azure DevOps, including Pipelines (CI/CD), Repos, Boards, and Artifacts, for day-to-day development, build, and release management.

- Practical, day-to-day experience using AI coding tools within a .NET/Visual Studio workflow — e.g., GitHub Copilot (Visual Studio / VS Code), Cursor, Claude Code, Azure OpenAI Service, ChatGPT/other LLM-based assistants — not just awareness, but demonstrable use in real projects.

- Understanding of prompt engineering fundamentals and how to structure prompts/workflows for consistent, reliable output from AI tools.

- Working knowledge of the broader AI/LLM tooling landscape: code generation, AI-assisted testing and QA tools, AI-powered code review tools, and documentation/automation tools.

- Familiarity with modern SDLC practices on Azure DevOps: Agile/Scrum boards, branching strategies, automated build/release pipelines, and code review processes (pull requests).

- Strong understanding of software quality fundamentals — you know how to evaluate whether AI-generated code is actually correct, secure, performant, and maintainable, not just “working.”

- Good communication skills, with the ability to document and share AI-workflow learnings with the wider team.

- A pragmatic, product-first mindset: comfortable using AI tools to move quick, while knowing when to slow down and apply careful engineering judgement

📌 Ai Engineer (.Net + Claude) (Delhi)
🏢 Espire Infolabs
📍 Delhi