Software Engineer (RAG and LLM)

Software Engineer - AI

Our client is replacing outdated manual local government workflows with modern software used by hundreds of government agencies across the United States. With cutting-edge AI-powered software they are replacing manual data entry to eliminate delays backlogs and errors. This work directly impacts how communities fund schools infrastructure and public services.

About the Role

Were hiring an AI Engineer to help build the systems behind the AI conversation engine and automation platform.

Youll design and scale AI systems that generate responses retrieve relevant knowledge and connect LLM workflows to real government data systems.

This is a role for engineers who enjoy building production AI systems with real applications and impact not just prototypes.

Our client doesnt have QA teams dedicated designers or product managers. They believe the best software is built by engineers who are empowered to own the entire journey. Within the company you arent just executing on a spec; you are the architect the designer and the guardian of your code. You will scope the solution build the interface and support the production systems that keep local governments running. If you thrive in ambiguity and find hand-offs more frustrating than fulfilling youll fit right in. If you prefer a neatly defined roadmap and a team to catch bugs before they ship theyre likely not the right place for you.

What You Will Work On

Examples of problems our AI engineers tackle:

• Designing scalable RAG pipelines for government knowledge bases
• Building conversation engines with memory context and state
• Implementing LLM tooling and function-calling for system integration
• Designing evaluation harnesses and datasets for AI feature quality
• Preventing hallucinations and improving grounded response generation
• Scaling AI features across hundreds of government environments

Tech Stack

• Backend: Python
• Data: PostgreSQL
• AI Systems: LLMs embeddings vector retrieval RAG pipelines
• Infrastructure: AWS Docker
• Developer Tools: GitHub Linear Claude Code Cursor CI/CD automated testing

We understand that engineers may not be an expert in all of these technologies day one. They value engineers with a growth and learning mindset.

Your Role

• Build and evolve our Conversation Engine: powering pre-drafted email chat and voice responses including conversation state memory and high-quality response generation.
• Own the RAG pipeline end-to-end: document ingestion chunking strategies embeddings indexing retrieval (hybrid/vector) reranking and grounded response generation.
• Implement AI Tooling / function calling: connect LLM workflows to internal systems (e.g. account lookup case context retrieval knowledge base queries) with strong validation and safe execution patterns.
• Design evaluation and quality systems for AI features: offline eval harnesses golden datasets human feedback loops monitoring for hallucinations/grounding and regression prevention.
• Collaborate with cross-functional teams to define design and ship new features.
• Work closely with business stakeholders and customers to translate requirements into technical specifications and documentation.
• Mentor and support engineering team members promoting team efficiency and growth.
• Troubleshoot and debug complex issues ensuring timely resolution and platform stability.
• Optimize application performance reliability and scalability and uphold high standards for clean maintainable code.
• Identify and proactively address technical debt and performance bottlenecks to drive iterative product improvement.

What Were Looking For

• 2 years of experience building production software with strong proficiency in Python programming
• 2 years of experience working with and optimizing relational databases (e.g. SQL PostgreSQL).
• Experience with cloud infrastructure (AWS or similar)
• Proven experience working with Large Language Models (LLMs) and building production-ready RAG pipelines.
• Strong proficiency in API design data modeling relational database design and testing methodologies.
• Proficiency with modern DevOps practices: version control (Git) containerization (Docker) CI/CD (GitHub Actions) and automated testing frameworks.

Most importantly we look for engineers who:

• Care about building reliable AI systems in production
• Enjoy working on complex real-world problems
• Take ownership of systems from ideation to deployment

Benefits

• Competitive compensation and stock equity plan
• Comprehensive benefits package that includes medical dental vision and life insurance
• Company sponsored pre-tax retirement savings program (401k)
• A flexible work environment that supports working from home
• Flexible PTO
• Parental Leave
• Home office stipend

Required Experience:

IC