• Design, build, and iterate on AI-powered features — from prototype to production
• Develop and maintain LLM-based pipelines including RAG systems, agents, and prompt engineering frameworks
• Fine-tune, evaluate, and benchmark models for domain-specific tasks
• Build robust backend APIs and microservices that serve AI capabilities at scale
• Collaborate with product and design to translate AI capabilities into intuitive user experiences
• Integrate third-party AI services (OpenAI, Anthropic, Cohere, HuggingFace, etc.) and manage their trade-offs
• Instrument AI systems with monitoring, logging, and evaluation metrics to track quality over time
• Contribute to internal tooling, reusable components, and best practices for AI development

AI / ML:

LLM APIs & prompt engineering

RAG pipelines & vector databases

Model fine-tuning (LoRA, PEFT)

Evaluation frameworks & evals desi...