AI Software Engineer

Software Engineer – Backend AI / LLM Applications

Location: Dallas, TX or Houston, TX

Work Model: Hybrid

Employment Type: Contract-to-Hire

Sponsorship: Not available now or in the future

We’re looking for a Software Engineer to help build production AI features powered by large language models. This is a hands‑on engineering role focused on backend development, APIs, services, and integrating AI functionality into real applications used across the business.

This is not a research role or a prompt‑only position. The team needs someone who can build reliable backend systems, work with LLM APIs, support RAG‑based features, and help deploy AI functionality into production environments.

The ideal candidate is a backend‑focused engineer with strong Python, Java, or similar experience, plus hands‑on exposure to LLMs, RAG, embeddings, vector search, or AI API integrations.

• Build backend services and APIs that integrate LLMs into business applications
• Develop AI‑powered features using retrieval‑augmented generation/RAG
• Work with structured and unstructured data to support AI features
• Integrate AI functionality into existing applications and workflows
• Build scalable services using APIs, async processing, queues, and microservices patterns
• Help improve AI features around latency, retrieval quality, cost, and reliability
• Deploy, monitor, troubleshoot, and improve production applications
• Partner with engineering, data, and product teams to deliver usable AI solutions

• Backend software engineering experience with Python, Java, or similar
• Experience building APIs, backend services, microservices, or distributed applications
• Hands‑on exposure to LLMs, AI APIs, RAG, embeddings, vector search, or semantic search
• Experience building and shipping software beyond prototypes or school projects
• Familiarity with cloud environments such as AWS, Azure, or similar
• Strong understanding of production reliability, monitoring, testing, and scaling
• Ability to work hybrid in Dallas or Houston
• Must be authorized to work in the U.S. without sponsorship now or in the future

• Experience with FastAPI, Flask, Django, Spring Boot, or Node.js
• Experience with Lang Chain, Llama Index, OpenAI, Azure OpenAI, or similar
• Familiarity with Pinecone, Weaviate, FAISS, Chroma, or other vector databases
• Experience improving retrieval quality through chunking, ranking, filtering, or evaluation
• Experience building internal AI tools, copilots, chatbots, automation tools, or document search applications

This is a strong opportunity for a backend engineer who wants to move deeper into applied AI and production LLM development. You’ll be building real AI features, not just prototypes, and working on practical problems around APIs, RAG, scalability, reliability, and enterprise application integration.

The role is contract‑to‑hire, with the goal of converting into a long‑term position based on performance and business need.