Generative AI Engineer
$49 - $54 USD hourly
Role Description
Design, develop, and deploy enterprise-grade Generative AI and LLM applications, taking use cases from prototype to production, including data preparation, prompt design, retrieval, model integration, evaluation, deployment, monitoring, and optimization.
Roles & Responsibilities
Build RAG solutions using enterprise documents and structured/unstructured data.
Develop AI agents and multi-step agentic workflows with tool/function calling.
Integrate LLMs using Azure OpenAI, OpenAI, or Hugging Face.
Implement document ingestion, chunking, embeddings, metadata filtering, semantic/hybrid search, and reranking.
Develop backend services and REST APIs using Python and FastAPI.
Apply prompt engineering, structured outputs, few-shot prompting, context management, and guardrails.
Evaluate LLM applications for accuracy, groundedness, relevance, latency, and cost.
Implement production observability and monitoring.
Collaborate with engineering, data, product, security, and business teams while following responsible AI, security, privacy, and data-governance practices.
Essential Skills
Generative AI and Large Language Models (LLMs)
Retrieval-Augmented Generation (RAG)
AI Agents and Agentic Workflows
Embeddings and Semantic/Hybrid Search
Python and FastAPI
Prompt Engineering and Guardrails
LLM Evaluation, Monitoring, and Optimization
Azure OpenAI, OpenAI, or Hugging Face
Desirable Skills
Experience developing and deploying production-grade GenAI applications.
Experience with structured and unstructured enterprise data.
Experience Required
Overall Experience: 5β8 years
Software/ML Engineering Experience: 3β4 years, as specified in the original requirement.