Trace3
Software Engineer | AI & Automation
About this role
Trace3 seeks a Software Engineer specializing in AI and automation to design and deploy intelligent applications, APIs, and workflows that leverage large language models to streamline business processes. Working primarily in Python within the Microsoft Azure ecosystem, you'll build production-grade solutions including AI agents and copilots across multiple business functions.
What you'll do
- Design, develop, test, and maintain production software applications and AI-powered solutions using Python
- Integrate large language models into applications and build AI agents, copilots, and intelligent workflows
- Build backend services, APIs, and enterprise integrations with platforms like Microsoft 365, ServiceNow, and NetSuite
- Implement AI techniques including RAG, prompt engineering, embeddings, and function calling
- Translate business requirements into scalable technical solutions with proper testing and security practices
- Evaluate and optimize AI application performance, accuracy, reliability, and cost
What they're looking for
- Python development
- Large language models (LLMs) and generative AI
- API design and development
- Microsoft Azure cloud platform
- Enterprise system integration
- Software testing and debugging
- Prompt engineering and RAG techniques
- Database design and querying
Opens the application — the Jobs AI extension fills it for you. Set up autofill
Opens the official application on the employer’s site. No login required.
Trace3
Trace3 builds and optimizes complex defense and military systems, including battle management platforms, sensor resource management solutions, and enterprise system architectures for DoD programs. The company is hiring Systems Engineers, Performance Assessment Engineers, Software Engineers, and Test Engineers to design, develop, analyze, and validate these critical defense systems.
- Website
- trace3.com
Likely interview questions
- Describe your experience building production applications with large language models—what were the key challenges you encountered?
- How have you approached prompt engineering and RAG implementations to improve AI application accuracy?