LLM Integration Engineer
People Foundry
Delhi, India3h agovia LinkedIn
About the Role
The LLM Integration Engineer is a full-time, on-site role based in Delhi, India. This position is responsible for designing, developing, and integrating Large Language Model (LLM) capabilities into existing and new software systems.
Key Responsibilities
- Creating APIs and services for LLM interaction.
- Building data pipelines and workflows.
- Ensuring secure and efficient deployment of LLM-based features.
- Troubleshooting integration issues.
- Optimizing system performance.
- Collaborating with product, data, and engineering teams to define requirements and deliver robust solutions.
- Documenting integration processes.
- Maintaining technical standards.
- Contributing to continuous improvement of LLM tooling and infrastructure.
Requirements & Tech Stack
- Software Development skills, including proficiency in one or more programming languages (such as Python, Java, or JavaScript) and experience building production-grade applications.
- Integration skills, including experience with APIs, microservices, and connecting third-party or AI services to existing platforms.
- Systems Engineering skills to design, deploy, and maintain scalable, secure, and resilient architectures for LLM-based solutions.
- Experience working with LLMs or other machine learning models, including prompt engineering, model evaluation, and performance tuning, is highly beneficial.
- Familiarity with cloud platforms (e.g., AWS, GCP, Azure), containerization (Docker, Kubernetes), and CI/CD pipelines is an advantage.
Qualifications
- Strong Analytical Skills and Troubleshooting abilities to diagnose issues, interpret data, and improve system reliability.
- Bachelor’s degree in Computer Science, Engineering, or a related technical field, or equivalent practical experience, is preferred.
- Strong collaboration, communication, and documentation skills, with the ability to work closely with cross-functional teams and stakeholders.