Senior AI Developer

TL;DR

Senior AI Developer (GenAI/RAG): Building and deploying production-grade generative AI systems with an accent on agent orchestration, retrieval-augmented generation, evaluation, and cloud infrastructure. Focus on designing reliable LangChain and LangGraph workflows, optimizing vector search and model serving, and implementing security, governance, and observability for enterprise applications.

Location: Charlotte, North Carolina, United States; hybrid schedule with 3 days onsite and 2 days remote, Monday through Friday, 8:00 a.m. to 5:00 p.m.

Company

hirify.global provides staffing and technology services for organizations seeking specialized technical professionals.

What you will do

• Build and ship production generative AI and machine learning systems.
• Design agent workflows, state graphs, tools, retries, sub-graphs, and observability using LangChain and LangGraph.
• Develop RAG solutions with chunking, embeddings, hybrid retrieval, reranking, and evaluation.
• Deploy models and AI services on Vertex AI, including endpoints, pipelines, vector search, model management, IAM, and service architectures.
• Build Python or Node.js backends and React/Next.js interfaces.
• Implement cloud infrastructure, CI/CD, containerization, monitoring, security, and governance for AI products.

Requirements

• 7–10+ years of software engineering experience and 3–5+ years building production ML or GenAI systems.
• Expertise with LangChain, LangGraph, Vertex AI, RAG techniques, vector databases, and embedding models.
• Production backend development with Python and FastAPI or Node.js, plus React/Next.js experience.
• Experience with GCP, Docker, Kubernetes, CI/CD, GenAI evaluation, observability, and prompt/version management.
• Knowledge of PII handling, data isolation, data residency, prompt-injection defenses, and secret management.
• Strong communication skills and a track record of turning ambiguous requirements into shipped products.

Nice to have

• Knowledge graphs using RDF/OWL, retrieval planning, and toolformer or agent patterns.
• LLM serving and routing, mixture-of-experts, function and tool calling, Guardrails, Instructor schemas, and Pydantic.
• Experience with LlamaIndex, structured SQL/Graph RAG, and integrations with databases or SaaS tools.

Culture & Benefits

• Hybrid work arrangement with three onsite days and two remote days each week.
• Regular weekday schedule from 8:00 a.m. to 5:00 p.m.
• Opportunity to build enterprise AI products and production systems.