Job Title: LLM Engineer
Location: 100% Onsite – Houston, TX
Employment Type: Long Term Contract, 24-36+ Months
About the Project
This project is a cutting-edge initiative focused on integrating Generative AI (GenAI) capabilities into over 120 in-house applications, with a goal of full AI adoption across the enterprise. Currently serving 600–800 users, the project aims to expand to over 1,000 additional users in 2026. Users range from field personnel to engineers and managers, requiring robust, scalable, and intuitive AI-powered solutions.
Role Overview
We are seeking a highly skilled LLM Software Engineer to join our team onsite in Houston. This individual will play a key role in designing, developing, and deploying Large Language Model (LLM) features into existing applications. The ideal candidate will have hands-on experience with GenAI projects, particularly in transforming natural language inputs (emails, voice, Teams conversations) into SQL queries that drive intelligent automation and reasoning within applications.
Key Responsibilities
- Design and implement LLM-powered features that automate tasks and enhance user interaction within enterprise applications.
- Develop NLP pipelines that convert natural language queries into structured SQL for data retrieval and reasoning.
- Collaborate with cross-functional teams to integrate LLMs into existing data pipelines and application architectures.
- Build and deploy chat agents/bots that utilize generated SQL to provide intelligent responses.
- Contribute to backend development using Python and frontend components using TypeScript.
- Participate in architectural decisions, especially around database design and AI integration.
Must-Have Qualifications
- 5+ years of software engineering experience (open to 3+ years for exceptional candidates with strong culture fit and intangibles).
- Proven experience working on GenAI projects, especially those involving LLM deployment in production environments.
- Strong background in Natural Language Processing (NLP).
- Experience designing, building, and deploying LLMs within applications.
- Proficiency in Python (backend-focused development).
- Experience with TypeScript for frontend or full-stack development.
- Solid understanding of database architecture and design.
- Demonstrated ability to convert conversational inputs (email, voice, chat) into SQL queries.
Preferred Skills
- Experience working with enterprise-scale applications and diverse user bases.
- Familiarity with cloud platforms and containerization (e.g., Docker, Kubernetes).
- Knowledge of data security and compliance in AI applications.
- Strong communication and collaboration skills.
