Software Engineer - LLM Platforms
Turing
Palo Alto, CA, USA (Remote)
Sep 2024 – Present
Lead engineer within an applied research pod translating LLM breakthroughs into production-grade developer tooling.
- Designed inference orchestration services that auto-select optimal LLM providers, shaving 28% off infrastructure spend while keeping sub-second latency guarantees.
- Implemented retrieval evaluation harnesses and prompt analytics that improved answer correctness by 18% across client deployments.
- Partnered with MLOps and compliance teams to deliver SOC2-ready audit trails, rate limiting, and encrypted artefact storage for enterprise integrations.