Gen AI Engineer / LLM Engineer (Onsite Sunrise, FL)
Role Overview
We are seeking a GenAI / Agentic AI Engineer to design and build cutting-edge AI-driven solutions for enterprise use cases. You will work on LLM-powered applications, agent workflows, and scalable AI pipelines that directly impact business operations.
Key Responsibilities
Design and implement Generative AI / Agentic AI solutions including:
Prompt engineering
Tool orchestration
Retrieval (RAG) pipelines
Reasoning chains & human-in-the-loop workflows
Build production-grade AI pipelines:
Data ingestion embeddings model APIs orchestration frameworks
Integrate with enterprise systems (upstream/downstream)
Collaborate with AI Tech Leads & Product Teams to:
Translate business requirements into scalable AI solutions
Rapidly prototype and deploy AI workflows
Ensure quality, safety, and observability:
Model evaluation metrics
Prompt/version management
Guardrails & grounding strategies
Logging & performance tuning
Support enterprise readiness:
Documentation & knowledge transfer
Incident triage & continuous improvements
Required Skills
Strong programming in Python
Hands-on experience with LLMs / Generative AI applications
Experience with at least one:
LangChain / LangGraph
Semantic Kernel
CrewAI / AutoGen / LlamaIndex
Solid understanding of:
RAG (Retrieval Augmented Generation)
Embeddings & vector databases
AI orchestration / agent workflows
Experience with:
MLOps / LLMOps
CI/CD for AI pipelines
Model & prompt lifecycle management
Preferred Skills
Experience with OpenAI / Azure OpenAI / AWS Bedrock / Vertex AI
Knowledge of evaluation frameworks, observability tools
Exposure to enterprise AI deployments in financial services
Never miss an opportunity! Create an alert based on the job you applied for.
