About this role
Build and evaluate agentic AI systems that integrate foundation models, retrieval, simulation, external tools, and deterministic verification to support planning and decision-making. Responsibilities include fine-tuning and evaluating models, developing multi-agent workflows and retrieval pipelines, designing experiments and benchmarks, and partnering with engineers and domain experts to transition prototypes to production-ready capabilities.
Skills for this role
PythonPyTorchTransformersvLLMHugging FaceFine-tuning language modelsModel evaluationRetrieval-augmented generationEmbeddingsVector searchKnowledge retrieval systemsMulti-agent systemsAgentic AI systemsTool-calling workflowsMulti-step reasoning pipelinesDistillationReinforcement LearningSimulation integrationExperiment designBenchmarkingDataset constructionRetrieval pipelinesAutomated benchmarksReproducible researchHuman-machine teamingExplainabilityTraceabilityUncertainty estimation