AI/ML Engineer focused on LLM systems, applied research, and ML infrastructure
I build production-grade AI systems with a focus on LLM applications, RAG, orchestration, evaluation, and scalable infrastructure, while also exploring research questions around how these systems can be made more capable, reliable, and measurable.
- I build AI systems end-to-end, from ingestion and retrieval pipelines to orchestration, evaluation, and deployment.
- My work sits at the intersection of machine learning, backend engineering, product, and research.
- I’m particularly interested in research-driven engineering: building systems that not only work in production, but also help surface better questions, better methods, and better evaluation.
- My current focus includes conversational AI, analytics agents, multi-provider LLM platforms, and emerging research directions in modern AI systems.
- I care about systems that are not only useful, but also reliable, observable, scalable, and grounded in careful experimentation.
- Large Language Models (LLMs)
- Retrieval-Augmented Generation (RAG)
- Embeddings and vector search
- NLP and deep learning
- Evaluation and observability for AI systems
- Fine-tuning and experimentation workflows
- Benchmarking and research prototyping