Senior AI Software Engineer - LLM Applications (Azure)

Company Description

Work with Us. Change the World.

At AECOM, we're delivering a better world. Whether improving your commute, keeping the lights on, providing access to clean water, or transforming skylines, our work helps people and communities thrive. We are the world's trusted infrastructure consulting firm, partnering with clients to solve the world’s most complex challenges and build legacies for future generations.

There has never been a better time to be at AECOM. With accelerating infrastructure investment worldwide, our services are in great demand. We invite you to bring your bold ideas and big dreams and become part of a global team of over 50,000 planners, designers, engineers, scientists, digital innovators, program and construction managers and other professionals delivering projects that create a positive and tangible impact around the world.

We're one global team driven by our common purpose to deliver a better world. Join us.

Job Description

We’re hiring a Senior AI Software Engineer to design and build enterprise-grade AI applications powered by modern LLM architectures and Azure cloud technologies.

This role sits at the intersection of full-stack engineering and applied AI, focused on delivering scalable, production-ready systems using tools like Semantic Kernel, Kernel Memory, and Retrieval Augmented Generation (RAG).

You’ll be building an internal, enterprise LLM-powered chat platform used across the organization, delivering real-world AI solutions at scale, not prototypes. This role requires a pragmatic, solution-oriented mindset, strong communication across teams, and the ability to thrive in fast-paced environments while pushing forward modern AI capabilities.

This position will offer flexibility for hybrid work schedules to include both in-office presence and telecommute/virtual work, to be based from either Houston or Dallas, TX.

Key Responsibilities

Build & Deliver

• Develop scalable applications using C#, .NET, REST APIs, and Angular
• Design and optimize SQL Server data models, queries, and performance
• Write secure, maintainable, production-quality code with a focus on balancing speed and quality

AI Engineering

• Design and implement RAG pipelines and LLM-powered workflows
• Integrate multiple LLMs into enterprise applications
• Build and deploy agentic AI solutions
• Leverage Azure AI services (Semantic Kernel, Kernel Memory, AI Foundry)
• Contribute to evolving architectures such as Model Context Protocol (MCP) and multi-model orchestration

Cloud & Systems

• Deploy and operate applications in Azure with a focus on reliability, scalability, and cost efficiency
• Contribute to system design, architecture, and performance optimization

Collaboration

• Partner with architects and engineers in an Agile environment
• Translate business needs into scalable technical solutions and clearly communicate trade-offs to both technical and non-technical stakeholders

Innovation

• Evaluate and adopt emerging AI and GenAI technologies
• Continuously improve engineering practices across design, development, and delivery
• Bring a passion for AI and cloud-native development into day-to-day work

Qualifications

Minimum Qualifications

• Bachelor's Degree plus at least 6 years of software development experience building applications with C#/.NET and REST APIs, or demonstrated equivalency of experience and/or education
• Experience with Angular (modern versions)
• Strong SQL Server expertise (data modeling, performance tuning)
• Hands-on experience with LLMs and RAG architectures
• Experience with frameworks like Semantic Kernel, Kernel Memory, or similar
• Strong foundation in software engineering, system design, and architecture
• Self-driven with the ability to operate effectively in fast-paced, evolving environments

Preferred Qualifications

• Experience building or contributing to LLM-powered applications (e.g., chat systems, copilots)
• Familiarity with embeddings, vector databases, or prompt engineering
• Exposure to Model Context Protocol (MCP) or similar emerging LLM integration patterns
• Experience with multimodal AI (e.g., speech, vision, or document understanding)
• Experience with CI/CD (Azure DevOps, GitHub Actions) and containerization (Docker)

Additional Information

• Relocation assistance is not available for this position
• Sponsorship for US work authorization is not available for this position, now or in the future.

About AECOM

AECOM is proud to offer comprehensive benefits to meet the diverse needs of our employees. Depending on your employment status, AECOM benefits may include medical, dental, vision, life, AD&D, disability benefits, paid time off, leaves of absences, voluntary benefits, perks, flexible work options, well-being resources, employee assistance program, business travel insurance, service recognition awards, retirement savings plan, and employee stock purchase plan.

AECOM is the global infrastructure leader, committed to delivering a better wor