Agentic Software Engineer

Bosch Group•Plymouth Charter Township, MI

2h•Onsite

About The Position

Bosch provides the aftermarket and workshops worldwide with a complete range of diagnostic and repair shop equipment and a wide range of spare parts for passenger cars and commercial vehicles. Its product portfolio includes products made as Bosch original equipment, as well as aftermarket products and services developed and manufactured in-house. In its “Automotive Service Solutions” operations, Bosch supplies testing and repair-shop technology, diagnostic software, service training, and information services. In it's Automotive Aftermarket division, Bosch employs more than 17,000 associates in 150 countries. Deliver business outcomes on existing MA/BDO3 platforms by combining strong software engineering discipline with effective orchestration of AI agents. The role focuses on practical delivery in brownfield environments where engineers must understand existing code, integrations, business rules, data flows, operational constraints, and architecture guardrails before making safe changes.

Requirements

5+ years of professional software engineering experience.
Strong hands-on experience delivering changes in complex brownfield enterprise applications.
Experience with C#, .NET Framework/.NET Core, ASP.NET, REST APIs, SQL Server, Azure services, and integration technologies.
Experience with Git, pull requests, CI/CD pipelines, automated testing, and production release practices.
Ability to work with incomplete documentation and reverse engineer behavior from code, tests, logs, databases, and business feedback.
Effective use of GitHub Copilot, Microsoft Copilot, coding agents, test generation tools, and documentation assistants.
Prompting and agent instruction design for engineering tasks.
Use of AI for impact analysis, code comprehension, refactoring, test creation, documentation, and troubleshooting.
Ability to validate, challenge, and improve AI-generated output.
Understanding of AI usage risks including hallucination, insecure code, missing edge cases, weak tests, stale context, and hidden integration dependencies.
Strong engineering discipline and quality ownership.
Practical problem solving in legacy and integration-heavy environments.
Human + AI collaboration mindset.
Attention to traceability, testability, security, and maintainability.
Ability to communicate implementation risks and tradeoffs clearly.
Continuous learning and willingness to improve agent workflows over time.

Responsibilities

Deliver new features, enhancements, defect fixes, integrations, and operational improvements across brownfield enterprise applications.
Translate Jira stories, BDD scenarios, business rules, architecture guidance, and test cases into working software.
Use AI agents to accelerate implementation while validating every generated output against business intent and technical standards.
Own end-to-end delivery from analysis through code, tests, pull request, release readiness, and production validation.
Direct AI agents to perform codebase discovery, dependency analysis, impact analysis, refactoring, code generation, test generation, documentation, and troubleshooting.
Create and improve reusable prompts, agent instructions, workflow templates, and context packages for recurring engineering tasks.
Review, correct, and integrate AI-generated code and artifacts using engineering judgment and established review practices.
Contribute improved system knowledge back into shared repositories so future agents and engineers become more effective.
Analyze existing application behavior, integration dependencies, data models, legacy business rules, configuration, logs, and operational constraints before making changes.
Preserve compatibility with existing business processes and upstream/downstream systems.
Identify technical debt, risky dependencies, test gaps, and modernization opportunities during normal delivery work.
Support incremental modernization such as framework upgrades, API enablement, cloud migration, component refactoring, and test automation.
Ensure delivered changes meet architecture standards, secure coding practices, performance expectations, and operational readiness requirements.
Create or update automated unit, integration, regression, API, security, and BDD-based tests where appropriate.
Validate AI-generated tests for meaningful coverage rather than accepting superficial test output.
Participate in code reviews, pull request reviews, deployment preparation, CI/CD execution, and production support.
Use Azure DevOps, Git, CI/CD pipelines, observability tools, and deployment automation to deliver reliable software.
Use AI-assisted log analysis and root cause investigation to speed incident response and operational support.
Improve documentation, runbooks, monitoring queries, and support knowledge based on delivery and production learning.