Senior AI Engineer
veralto
Job Description
- Design and scale agentic AI systems to support long-running, complex workflows using orchestration frameworks such as LangGraph, CrewAI, or AutoGen.
- Develop systematic evaluation and benchmarking pipelines using G‑Eval, RAGAS, and LLM‑as‑a‑Judge approaches to measure performance, hallucinations, and latency.
- Implement advanced retrieval-augmented generation (RAG) strategies, including multi-stage re‑ranking, hybrid search, and query expansion for high-precision knowledge retrieval.
- Optimize model inference performance using quantization approaches such as AWQ and GGUF, along with caching strategies for cost‑efficient high throughput.
- Collaborate closely with Data Science and DevOps teams to transition experimental prototypes into hardened, production-ready APIs.
- Implement safety guardrails, red‑teaming workflows, and alignment mechanisms to ensure outputs meet industry regulations and brand‑safety standards.