Staff Software Engineer, Agentic AI Systems

The Role

Are you a software engineer who has honed your craft, technical leadership, and execution over years building and improving production systems, and are looking to apply your skills at the cutting edge of AI agents? This may be the role for you.

As a staff software engineer on our "agent lab" Natural Language Understanding team, you will play a central role in our mission: to advance the frontier of work that can be entrusted to agents to perform reliably at scale. You will have the opportunity to lead the evolution of the Moveworks AI Assistant platform in several of the following areas: agent orchestration, sandboxed file systems and code execution, latency optimization, agent memory, LLM self-reflection and improvement, execution environment simulation, enterprise knowledge graphs, and multimodal I/O.

You will have all the tools of modern enterprise AI at your disposal, including best-in-class LLMs from providers like OpenAI. Our team indexes on moving fast on scalable infrastructure, solving challenging product and engineering challenges, and pushing the envelope of value provided to customers. If you are looking to do the best work of your career with a bright, dedicated, and impact-driven team alongside you, we'd love to have a conversation.

What You Will Do:

• Lead and take on exciting and difficult engineering challenges (see areas listed above) to build and evolve capable AI agent systems that are reliable in every sense of the word
• Define, drive, and deliver frontier AI distributed systems and ensure they are productionized at scale, or use the latest advances in machine learning, LLMs, and AI agents to enhance our products and create delightful user experiences
• Set technical direction, influence roadmap, and drive the evolution of engineering areas of broad scope and impact to create lasting value for all our customers
• Set a high bar for writing robust, extensible, readable, and performant code, and raise the engineering standard for the team
• Partner with senior subject matter experts across the company including in machine learning, security, product, user experience, and customer success, to align teams and build the best enterprise AI products the world has ever seen
• Mentor and develop engineers on the team, including coaching on technical design, execution, and engineering excellence
• Collaborate deeply with machine learning engineers to define end-to-end system architecture and help build world-class AI systems

What You Bring To The Table:

• 6+ years experience designing, building, and improving production systems, ideally at scale
• Demonstrated ability to lead technical design and execution across multiple projects and stakeholders
• Ability to think and communicate clearly about complex engineering problems and systems, and to drive alignment across teams
• Comfort giving and receiving feedback, and in holding yourself and your coworkers accountable to a high standard of operational excellence
• Readiness to hit the ground running in a Mac development environment, programming in Python, Golang, and/or Java
• Desire to ship at a startup pace with a high degree of ownership
• Strong attention to detail and a track record of shipping high-quality, production-grade systems
• Strong appetite for continuous incremental wins and completing challenging projects fast
• High level of curiosity about engineering outside of immediate discipline and ongoing desire to learn and stay at the cutting edge of applied AI

Nice To Have:

• Experience building with LLMs, particularly in iterating on prompts, on model selection, on cognitive architecture design, and on latency/correctness tradeoffs in a data-driven way
• Hands-on experience driving one or more stages of a machine learning problem-solving lifecycle, such as experiment setup, dataset curation, model training, offline evaluation and error analysis, deployment, and online evaluation
• Experience in AI fairness, privacy, permission controls, safety, and/or security
• Experience designing and operating large-scale, high-reliability systems with strong observability, SLOs, and on-call excellence