Principal Machine Learning Engineer (Memory & Context)

This position is listed on behalf of a partner company, which manages all applications and next steps. Our partner is looking for a Principal Machine Learning Engineer (Memory & Context) based in the United States.
As a Principal Machine Learning Engineer, you will shape the memory and context capabilities behind advanced AI assistants, enabling them to deliver increasingly personalized and relevant experiences. You will design systems that help AI agents remember user preferences, understand evolving needs, and maintain continuity across conversations over extended periods. Working at the intersection of machine learning, LLM-based agents, and production engineering, you will own critical architectures from initial design through deployment and optimization. You will also develop evaluation frameworks to measure agent performance and guide data-driven improvements. In a fast-moving, technically ambitious environment, you will collaborate with senior engineers and cross-functional teams to turn emerging AI research into reliable, scalable products. This is an opportunity to establish technical direction, mentor engineering talent, and help redefine how people interact with intelligent assistants throughout their home-search journey.
\Define and own the architecture governing how AI assistants store, retrieve, update, and retire user memories across conversations, ensuring information remains relevant, useful, and reliable over time.
Lead context engineering:
Build and deploy AI agents:
Lead end-to-end development of production-grade agentic systems, covering orchestration, prompt engineering, context design, deployment, monitoring, and ongoing optimization.
Establish offline and online evaluation methodologies for memory quality, context relevance, and agent performance, using measurable results to guide technical decisions and product improvements.
Advance AI innovation:
Explore emerging agent architectures, memory systems, and long-context techniques, translating promising research into practical capabilities that enhance the user experience.
Own complex engineering initiatives, influence architecture and implementation decisions across teams, and establish best practices for building and operating reliable machine learning systems.
Partner with engineering, product, and other technical stakeholders to align priorities, clarify requirements, resolve dependencies, and deliver scalable solutions.
Share technical expertise through design reviews, code reviews, and mentoring while helping colleagues strengthen their capabilities in machine learning and agentic AI.
Present architectural decisions, evaluation findings, project progress, and strategic recommendations clearly to engineers, partner teams, and senior leadership.
Masters degree or higher in Computer Science, Electrical Engineering, or a related technical discipline, or equivalent practical experience.
Machine learning experience:
At least five years of experience deploying large-scale machine learning systems, including at least one recent year building and shipping LLM-based agents in production.
Hands-on expertise building AI agents, including orchestration, prompt engineering and optimization, and context engineering.
Demonstrated experience evaluating agentic systems and applying evaluation results to improve their quality, reliability, and effectiveness.
Programming skills:
Strong proficiency in Python and familiarity with agentic AI frameworks such as LangGraph, Agents SDK, or AutoGen.
Experience designing long-term, episodic, or user-profile memory systems for AI agents.
Preferred conversational AI experience:
Research publications, patents, or open-source contributions involving agentic AI, memory architectures, or long-context models.
Compensation varies by location and depends on factors such as experience and performance.
Equity awards:
Eligibility for additional equity compensation, with award amounts determined by factors including experience, performance, and location.
Remote work flexibility:
Fully remote position for eligible U.Opportunities to build and scale advanced AI systems that support personalized experiences for millions of users.
Work with emerging LLM technologies, agentic AI architectures, memory systems, and advanced machine learning techniques.
Opportunities to shape technical strategy, lead cross-functional initiatives, and mentor other engineering professionals.
Work alongside experienced engineers and multidisciplinary teams in an environment that values innovation, inclusion, and continuous improvement.
AI-powered matching process
to ensure your application is reviewed quickly, objectively, and fairly against the roles core requirements. Data Privacy Notice:
By submitting your application, you acknowledge that Jobgether will process your personal data to evaluate your candidacy and share relevant information with the hiring employer. This processing is based on legitimate interest and pre-contractual measures under applicable data protection laws (including GDPR).