Note: The job is a remote job and is open to candidates in USA. UtiliSave LLC is a utility bill auditing and cost recovery company expanding its investment in AI and cloud technology. The AI Platform Support Engineer will operate and maintain the production AI Assistant Platform, build and tune RAG and LLM workflows, support data and document extraction pipelines, and collaborate with technical and business stakeholders on platform improvements.
Responsibilities
- Support the day-to-day operation and maintenance of the AI Assistant Platform, including monitoring system health, triaging issues, and coordinating fixes with the development team
- Build and maintain RAG pipelines-chunking, embedding generation, vector indexing, retrieval tuning, and evaluation-to keep the knowledge base accurate and relevant
- Configure and refine LLM agent behavior, including instruction tuning, tool/Action Group testing, and prompt engineering to improve answer quality for auditor queries
- Assist with data pipeline tasks including metadata extraction, JSON generation, SQL loading, and semantic indexing
- Coordinate and execute testing cycles for AI features, collect structured feedback from auditors, and track resolution in JIRA
- Support document extraction workflows for utility bill processing, validating accuracy and expanding template coverage to new formats
- Evaluate, pilot, and recommend emerging AI tools and capabilities (e.g., Claude Code, Claude for Excel, Cursor IDE, Amazon Bedrock Agent Core) for adoption across the organization
- Maintain technical documentation for AI platform components, data flows, agent configurations, and operational runbooks
- Assist with cloud storage organization, data source management, and cost optimization across AI services
- Support future integration between the AI platform and CRM by helping define data exchange interfaces and testing data flows
- Collaborate cross-functionally with auditors, developers, and leadership to translate business needs into AI platform improvements
Skills
- 2–4 years of experience in a technical role involving AI/ML tools, cloud platforms, data engineering, or software development support
- Solid working knowledge of modern AI and LLM concepts, including prompt engineering, retrieval-augmented generation (RAG), embeddings, vector databases, and agent-based architectures
- Demonstrated experience building or operating RAG or embedding-based systems (from prototype to production)
- Hands-on experience with at least one major cloud platform (AWS, Azure, or GCP). Experience with AWS AI services (Bedrock, Q Business, Textract, S3) is a strong plus, but equivalent experience on other clouds is welcome
- Proficiency in Python (preferred) or JavaScript for scripting, data processing, and automation
- Experience with SQL databases for querying, loading data, and basic schema design
- Familiarity with work-tracking tools such as JIRA, Azure DevOps, or similar
- Strong communication skills, with the ability to document technical processes and communicate status to both technical and non-technical stakeholders
- Self-starter mentality, strong curiosity about AI advancements, and a willingness to learn quickly
- High attention to detail when working with data pipelines, configurations, and testing workflows
- Familiarity with AI-assisted development tools such as Cursor IDE, Claude Code, or GitHub Copilot
- Exposure to document extraction/OCR tools is a plus
- Bachelor's degree preferred but not required; equivalent hands-on experience accepted
Benefits
- Performance-based bonus
- Health, dental, and vision insurance
- 401(k) with company match
- Generous PTO
- 11 paid holidays
- Fully remote role
Company Overview