Gen AI Engineer

Jade Business Services (JBS); Houston (TX); On-site; USD 120,000 - 180,000; Full time

Job summary

Jade Business Services in Houston is seeking an AI Engineer - Generative AI / LLM with 3–7 years of hands-on experience to design and build AI-powered applications. You will work on scalable AI solutions using modern LLM frameworks and cloud tech, integrating AI into enterprise workflows.

You'll implement RAG, prompt engineering, language models such as OpenAI, Azure OpenAI, Claude, Gemini, and will collaborate across product, data science, and engineering to deliver production-ready APIs and

Qualifications

• 3-7 years of software/AI engineering experience.
• Strong programming experience in Python.
• Hands-on experience building Generative AI / LLM applications.
• Strong understanding of LLMs, Transformers, embeddings, prompt engineering, and NLP concepts.
• Hands-on experience with RAG architecture.
• Experience with at least one LLM framework such as LangChain, LangGraph, Semantic Kernel.
• Experience with one or more Vector Databases/Search technologies: Pinecone, FAISS, Chroma, Weaviate, Milvus.
• Experience working with SQL and databases.
• Experience with Git, CI/CD, Docker, and software development best practices.
• Strong understanding of API integration, authentication, logging, monitoring, and debugging.

Responsibilities

• Design, develop, and deploy Generative AI and LLM-powered applications.
• Build production-ready solutions using RAG and knowledge-based AI systems.
• Work with LLMs such as OpenAI GPT, Azure OpenAI, Claude, Gemini, Llama, or similar models.
• Develop AI workflows using frameworks such as LangChain, LlamaIndex, LangGraph, or equivalent.
• Implement prompt engineering, prompt optimization, structured outputs, and function/tool calling.
• Develop and integrate vector databases such as Pinecone, Azure AI Search, Weaviate, Chroma, Milvus, or FAISS.
• Build document ingestion and processing pipelines for PDFs, documents, web content, and enterprise data.
• Implement embeddings, semantic search, chunking, metadata filtering, and reranking.
• Develop APIs and backend services using Python, FastAPI, Flask, or Django.
• Integrate LLM solutions with enterprise applications, databases, APIs, and cloud services.
• Evaluate LLM performance using accuracy, relevance, hallucination, latency, and cost metrics.
• Implement responsible AI practices including security, data privacy, access control, and guardrails.
• Optimize AI applications for scalability, performance, reliability, and cost.
• Collaborate with data scientists, software engineers, architects, product teams, and business stakeholders.
• Troubleshoot and continuously improve AI models and applications based on production feedback.

Skills

Python

Generative AI

LLMs

Transformers

Embeddings

Prompt engineering

RAG

SQL

Git

CI/CD

Docker

API integration

Logging & monitoring

Debugging

Tools

LangChain

LangGraph

Semantic Kernel

Pinecone

FAISS

Chroma

Weaviate

Milvus

OpenAI

Azure OpenAI

Docker

Kubernetes

Job description

We are looking for a skilled AI Engineer - Generative AI / LLM with 3-7 years of experience in designing and developing AI-powered applications. The ideal candidate should have strong hands-on experience with Generative AI, Large Language Models (LLMs), RAG, prompt engineering, and Python.

The candidate will work on building scalable AI solutions using modern LLM frameworks and cloud technologies, integrating AI capabilities into enterprise applications and business workflows.

Key Responsibilities

• Design, develop, and deploy Generative AI and LLM-powered applications.
• Build production-ready solutions using RAG (Retrieval-Augmented Generation) and knowledge-based AI systems.
• Work with LLMs such as OpenAI GPT, Azure OpenAI, Claude, Gemini, Llama, or similar models.
• Develop AI workflows using frameworks such as LangChain, LlamaIndex, LangGraph, or equivalent.
• Implement prompt engineering, prompt optimization, structured outputs, and function/tool calling.
• Develop and integrate vector databases such as Pinecone, Azure AI Search, Weaviate, Chroma, Milvus, or FAISS.
• Build document ingestion and processing pipelines for PDFs, documents, web content, and enterprise data.
• Implement techniques such as embeddings, semantic search, chunking, metadata filtering, and reranking.
• Develop APIs and backend services using Python, FastAPI, Flask, or Django.
• Integrate LLM solutions with enterprise applications, databases, APIs, and cloud services.
• Evaluate LLM performance using appropriate accuracy, relevance, hallucination, latency, and cost metrics.
• Implement responsible AI practices including security, data privacy, access control, and guardrails.
• Optimize AI applications for scalability, performance, reliability, and cost.
• Collaborate with data scientists, software engineers, architects, product teams, and business stakeholders.
• Troubleshoot and continuously improve AI models and applications based on production feedback.

Required Skills

• 3-7 years of software/AI engineering experience.
• Strong programming experience in Python.
• Hands-on experience building Generative AI / LLM applications.
• Strong understanding of LLMs, Transformers, embeddings, prompt engineering, and NLP concepts.
• Hands-on experience with RAG architecture.
• Experience with at least one LLM framework such as:
• LangChain
• LangGraph
• Semantic Kernel
• Experience with one or more Vector Databases/Search technologies:
• Pinecone
• FAISS
• Chroma
• Weaviate
• Milvus
• Experience working with LLM providers such as OpenAI/Azure OpenAI, Anthropic, Google Gemini, AWS Bedrock, or open-source LLMs.
• Good understanding of SQL and databases.
• Experience with Git, CI/CD, Docker, and software development best practices.
• Strong understanding of API integration, authentication, logging, monitoring, and debugging.

Preferred / Nice-to-Have Skills

• Experience with AWS, Azure, or GCP.
• Experience with Kubernetes and containerized AI applications.