Role overview
Roller is looking for a talented AI Engineer with 3-5 years of experience to help build the AI platform and intelligent automation systems enabling AI powered business verticals. The ideal candidate will have hands-on experience designing and deploying GenAI platform and solutions using modern LLM frameworks, RAG architectures, and scalable AI pipelines.
What you'll work on
- Develop Enterprise GenAI platform and services for various business verticals using Python and modern frameworks such as LangChain.
- Design and implement Retrieval Augmented Generation (RAG) systems using vector databases and LLMs.
- Build scalable AI pipelines for ingestion, embedding, retrieval, and generation workflows.
- Integrate LLMs with enterprise data sources and APIs.
- Implement LLM evaluation frameworks to measure model performance, hallucination, and response quality.
- Establish AI governance and Guardrails practices including safety checks, monitoring, and responsible AI controls.
- Optimize prompt engineering strategies and model interactions for accuracy and performance.
- Implement observability for AI systems and build AI usage dashboards for prompt tracing, token usage monitoring, latency tracking, Agent usage and evaluation metrics.
- Collaborate with cross functional teams to deploy production-grade AI solutions.
What we're looking for
- Experience with workflow automation tools such as n8n.
- Experience deploying LLM systems in production environments.
- Advanced skills such as LLM Fine tuning, Self LLM hosting, Voice AI.
- Familiarity with cloud AI platforms (AWS, GCP, Azure).
- Venue management domain experience.
Tags & focus areas
Used for matching and alerts on DevFound Ai Engineer Ai