- Own AI/ML features end-to-end including research, prototyping, production, monitoring, and iteration.
- Design and build LLM-powered features like feedback categorization, summarization, reply generation, semantic search, anomaly detection, and agentic scenarios.
- Manage commercial LLM API integrations and open-source model selection, adaptation, fine-tuning, and deployment.
- Build and maintain pipelines for model training, fine-tuning, and quality evaluation, including metrics, offline evals, LLM-as-a-judge, and A/B tests.
- Develop RAG and semantic search capabilities including embeddings and vector storage.
- Optimize quality, latency, and cost of LLM inference in production.
- Collaborate with backend, product, and platform teams to contribute to overall system architecture and write secure, documented, and testable code.
PythonSQLMachine Learning+3 more