Senior GenAI / LLM Engineer (Hands-on, Production)

We are looking for a hands-on Senior GenAI / LLM Engineer to build and own production-grade GenAI systems in a large, complex organizational environment.

This role is not research- or POC-focused. We are looking for someone who has built and maintained GenAI systems running in production, including RAG pipelines and LLM-based agents, and has dealt with real-world constraints such as scale, cost, security, and reliability.

Responsibilities

• Design, build, and maintain end-to-end GenAI / LLM systems in production.
• Own and evolve RAG architectures integrated with enterprise data sources.
• Build and operate LLM-based agents and AI workflows over time (not one-off demos).
• Architect solutions using commercial AI providers, open-source models, and private/on-prem environments.
• Ensure performance, scalability, cost control, security, and operational stability.
• Work closely with engineering leadership and internal stakeholders.

Requirements

• Hands-on experience building GenAI / LLM systems that are live in production.
• Practical experience with RAG architectures beyond experiments or demos.
• Experience working with commercial LLM providers (e.g., OpenAI, Azure OpenAI, Anthropic).
• Strong system-level and backend architectural experience.
• Ability to operate within organizational constraints (security, scale, reliability).

Nice to have

• Experience in large or regulated organizations.
• Technical leadership or mentoring experience.