Full-Stack AI Developer

Full Stack AI Engineer

Location: Charlotte NC (hybrid)

Employment Type: Fulltime

• We are seeking a Full Stack AI Engineer who combines strong software engineering fundamentals with applied AI creativity. This role plays a foundational part in shaping the company’s AI and automation strategy—architecting, building, and deploying intelligent tools that transform how the business operates.
• You will own full‑stack development of AI‑driven internal tools, partner directly with operators and business units, and help build an internal culture of AI adoption. This role requires high ownership, strong execution, and a passion for building practical, real‑world AI solutions.

• 4–7+ years of professional experience in software engineering with modern web frameworks.
• Strong Python experience in production environments.
• Experience shipping applied LLM features into production (not just prototypes), including summarization, extraction, classification, routing, or operator‑assist workflows.
• Experience building RAG systems end‑to‑end including document ingestion pipelines, chunking strategy iteration, retrieval, and context assembly.
• Experience building agent or tool‑calling workflows where models trigger tools or actions with clear contracts and safety boundaries.
• Experience delivering software used by real operators including review flows, exception handling, auditability, and measurable improvement.
• Strong communication and problem translation skills with the ability to turn ambiguous operational needs into deployable workflows with clear success metrics.
• Experience integrating with call center or transcript systems is preferred.
• Experience integrating with CRM or ERP platforms is preferred.
• Experience with evaluation practices for LLM systems such as sampling strategies, rubric‑based scoring, regression checks, and prompt versioning is preferred.
• Strong REST API design experience, with versioning best practices preferred.
• Experience with asynchronous processing and pipeline‑style workloads.
• Experience building internal or administrative user interfaces (React experience preferred).
• Familiarity with cloud deployment, CI/CD pipelines, and environment configuration.

• Design, prototype, and deploy full‑stack AI applications using Python frameworks (FastAPI/Django) and modern front‑end frameworks (React/Next.js).
• Develop AI‑powered capabilities including summarization, classification, routing, extraction, and workflow automation.
• Build operator‑facing tools such as review queues, exception handling, and traceability views to ensure AI outputs are trusted and usable.

• Design and implement reliable retrieval‑augmented generation (RAG) systems including ingestion pipelines, embeddings, vector search, and context assembly.
• Build scalable patterns for APIs, cloud deployment, CI/CD, and AI service orchestration.
• Anticipate and mitigate common LLM failure modes including irrelevant retrieval, missing context, hallucinated outputs, and stale data.

• Identify manual workflows across operations, sales, finance, and field teams and replace them with AI‑enabled automation.

• ingestion → retrieval → agent/tool execution → human review → measurement
• Design human‑in‑the‑loop workflows with clear escalation paths, editable outputs, and feedback capture.

• Build integrations with operational systems including Service Titan, call center platforms, and internal data systems.
• Develop transcript‑driven workflows such as call summaries, lead qualification insights, automated tagging, and routing.
• Ensure workflows operate reliably within real‑world constraints including messy data, timing dependencies, and operational handoffs.

• Develop agent‑based workflows that trigger tools to perform operational actions such as updating records, retrieving context, or triggering workflows.
• Implement safe tool‑calling patterns including defined input/output contracts, validation, retries, and permission scoping.
• Ensure systems remain observable through logging, intermediate traces, and measurable outcomes.

• Partner with operators, engineering teams, and leadership to identify high‑impact AI opportunities.
• Translate ambiguous business problems into deployable AI workflows.
• Communicate technical concepts clearly to non‑technical stakeholders and support AI adoption across the organization.