Machine Learning Engineer, Agentic Application

ServiceNow•Mountain View, CA

14h•Hybrid

About The Position

This role is within the Conversation Engine team at Moveworks, focusing on scaling and optimizing a cutting-edge Generative AI product for enterprise users. The position involves working at the core of Moveworks' Generative AI product, enhancing its scalability and robustness to meet the demands of the enterprise solution space. The engineer will collaborate with machine learning experts and cross-functional teams, leveraging user behavior data to drive innovation and solve complex problems. The challenge includes scaling the conversation engine to support millions of users across multiple chat channels and use cases, and improving the end-to-end product infrastructure with high engineering quality. This involves constructing extensive product infrastructure with user-friendly interfaces for customizing generative AI models, collecting data and feedback, adapting to diverse enterprise use cases, and delivering domain-specific conversational experiences. Additionally, the role requires designing scalable API abstractions for the conversation platform supporting popular chat clients and optimizing the dialog engine for real-time multilingual translation with minimal memory footprint and low latency.

Requirements

A strong foundation in computer science and software engineering, coupled with expertise in building scalable systems.
A deep understanding of clean, modular, and scalable API design.
Ability to champion best coding practices and influence fellow engineers to uphold high standards of code quality and craftsmanship.
Passion for optimizing systems and improving performance.
Well-versed in tracing, logging, and metrics frameworks, and possess a systematic approach to quickly identify and resolve latency bottlenecks, race conditions, and throughput limitations.
Ability to independently research new requirements and develop innovative solutions.
Thrive in an environment of fast-paced coding and execution, embracing rapid iterations to deliver results.
Strong communication skills to effectively articulate rationales and design approaches.
Cross-functional awareness that enables seamless collaboration with various teams.
A bachelor's degree or higher in computer science or a related field.
2+ years of professional development experience, specifically in building systems at scale.

Responsibilities

Scaling and optimizing the Moveworks Generative AI product.
Collaborating with machine learning experts and cross-functional teams to rapidly iterate over new ideas.
Leveraging user behavior data to make informed decisions.
Scaling and optimizing the conversation engine to support hundreds of millions of users across multiple chat channels and use cases.
Enhancing the end-to-end product infrastructure with engineering quality and robustness.
Constructing extensive product infrastructure with user-friendly interfaces for engineers and configurators to customize and optimize generative AI models.
Collecting data and feedback, adapting to diverse enterprise use cases and business contexts, and delivering domain-specific conversational experiences.
Designing scalable API abstractions for the conversation platform that supports all popular chat clients (e.g., MSTeams, Slack, Web) and offers a neutral API for other parts of the engineering system.
Optimizing the dialog engine to accommodate a wide range of conversational features, leveraging private domain knowledge unique to each enterprise customer in the cloud, and enabling real-time multilingual translation with minimal memory footprint, low latency, and a streamlined development process.
Championing best practices for coding patterns, API design, scalability, robustness, and optimization.
Fostering a culture of excellence and continuous improvements among fellow engineers.
Providing comprehensive insights and visibility into the performance of the conversational AI product by implementing a robust logging and tracing framework, user-friendly debugging and triaging tools, and automated metrics for efficient monitoring and analysis.
Collaborating closely with ML engineers, application engineers, product teams, and customer support teams to drive the development of new features and scalability initiatives.