Weβre looking for a senior software engineer with a strong proficiency in ML systems and large language models to help build advanced reasoning capabilities for the Siri virtual assistant. We are a collaborative team of ML engineers, scientists, and software developers passionate about LLM planner modeling to build the next generation of the Siri virtual assistant. Your work will center on developing reliable, scalable tooling for training, simulation, and evaluation of LLMs and agentic systems. Youβll also play a hands-on role in designing and running experiments in simulation, and integrating client-side components with backend systems into a production-ready testable environment.
This is an opportunity to work with pioneering technologies that push the boundaries of LLM agent reasoning, system architecture, and rapid iteration. Youβll collaborate closely with ML developers, client-side engineers, and deep learning leaders to bring enhanced LLM reasoning capabilities into production.
Bachelor's degree in Computer Science or related quantitative field, with at least 4+ years of relevant industry experience with the following:
Strong skills in Python (desired) and at least one other object-oriented programming language
Proven experience in software engineering, including system design, development, testing, debugging, release and maintenance
In-depth understanding of agent-based simulation frameworks, Agentic RAG systems, prompt engineering, and evaluation best practices for LLMs
Ability to develop long-term strategic visions and implement scalable solutions in fast-paced, agile work environments
Experience supporting ML teams or deploying LLM models in production or research
Knowledge of feedback mechanisms and adaptive agent behaviors
Experience integrating client-side applications or code with backend systems (APIs or custom protocols)
MS or advanced degree in Computer Science, Machine Learning or related quantitative filed is preferred