LLM Application Engineer
Artmac · Prosper, TX · 3 wk ago
On-siteEngineeringContract
About the role
Artmac Soft is a technology consulting and service-oriented IT company that provides innovative technology solutions and services to customers.
Job Title: LLM Application Engineer · Job Type: W2/C2C · Experience: 8+ Years · Location: Prosper, Texas
Responsibilities
- 8+ years of experience in LLM Application Engineer.
- Strong proficiency in Python and/or TypeScript.
- Hands-on experience integrating OpenAI, Anthropic Claude, Google Gemini, or similar LLM APIs.
- Strong understanding of Generative AI and Large Language Models.
- Hands-on experience designing and implementing RAG architectures.
- Experience designing and developing REST APIs and backend services.
- Strong understanding of API authentication, rate limiting, error handling, and integration patterns.
- Design and develop scalable LLM-powered applications for enterprise use cases.
- Build applications using Python and/or TypeScript with modern software engineering practices.
- Integrate and work with LLM APIs such as OpenAI, Anthropic Claude, and Google Gemini.
- Develop and optimize Retrieval-Augmented Generation (RAG) pipelines.
- Implement document ingestion, preprocessing, chunking, embeddings, retrieval, reranking, and context management workflows.
- Design and integrate vector databases for semantic search and knowledge retrieval.
- Develop robust APIs and backend services for LLM-powered applications.
- Implement prompt engineering strategies and reusable prompt templates.
- Design workflows for structured outputs, function/tool calling, and multi-step LLM interactions.
- Develop automated LLM evaluation and testing frameworks to measure quality, relevance, accuracy, latency, and reliability.
Qualifications
- Bachelor's degree or equivalent combination of education and experience.
Skills
- Python and/or TypeScript
- LLM API integration (OpenAI, Anthropic Claude, Google Gemini)
- Generative AI and Large Language Models
- RAG architecture design and implementation
- REST API and backend services development
- API authentication, rate limiting, error handling
- Vector databases for semantic search
- Prompt engineering and reusable templates
- Structured outputs, function/tool calling, multi-step LLM interactions
- Automated LLM evaluation and testing frameworks