- Design, develop, and deploy production-grade AI-powered backend systems.
- Integrate LLMs and traditional ML models into performant, scalable architectures.
- Integrate and optimize vector databases for RAG pipelines and traditional ML queries.
- Write clean, well-structured, testable Python code following best practices.
- Optimize performance and decision-making to reduce latency, including for heavy AI models.
- Build hybrid architectures that balance LLM calls with traditional ML.
- Debug issues spanning backend, AI inference, and UI integration.
- Conduct development testing before QA handoff.
- Collaborate with product, backend, and frontend engineers.
DockerPythonFlask+3 more