ML Engineer

The Cortex team • Sunnyvale, CA

2d

About The Position

The Cortex team is the core A.I. platform powering the vision of delivering the world’s best intelligent personal assistants to Client's’s customers, accessible via natural voice commands, text messages, rich UI interactions, and a mix of all of the above via multi-modal experiences. We believe conversations are a natural and powerful user interface for interacting with technology and enable a richer customer experiences -- both online and in-store. We are building and designing the next generation of Natural Language Understanding (NLU) services that other teams can easily integrate and leverage, and build rich experiences: from pure voice and text shopping assistants (Siri, Google Assistant, Text to Shop), to customer care channels, to mobile apps with rich, intertwined, multi-modal interaction modes. Interested in diving in? We need solid prompt engineers with the talent and expertise required to design, evaluate, improve and evolve our capabilities in at least some of the following areas: - Developing, testing and refining prompts for various applications, including text generation, question answering, data classification, and synthetic training data generation. - Develop and maintain principled regression test suites in order to adequately measure and ensure prompt compliance at scale, for mission critical applications. - Analyze and iterate on prompts, over time, based on performance metrics, user feedback and new product requirements. - Collaborating with legal, product and data science teams to align prompts with overall company goals and compliance. - Seamlessly navigate prompt characteristics of multiple model architectures (GPT, Llama, Gemini, our own fine-tuned LLMs) and versions (e.g. Llama2 vs. Llama 3). - Creatively attack your own prompts, to assess safety exposure and strengthen their compliance characteristics. - Continued research and education on the ever-changing AI field and emerging properties of large models. Come at the right time, and you will have an enormous opportunity to make a massive impact on the design, architecture, and implementation of an innovative, mission critical product, used every day, by people you know, and which customers love.

Requirements

• Solid data skills, sound computer-science fundamentals, and strong programming experience.
• Programming experience in Python
• Experience with at least one relational database technology such as MySQL, PostgreSQL, Oracle, or MS SQL.
• Deep hands-on technical expertise in development, preferably full-stack.
• Good data-processing and testing fundamentals. Principled approach to system updates and prompt compliance evaluation.
• Ability to take a project from scoping requirements through actual launch.
• Deal well with ambiguous/undefined problems
• A continuous drive to explore, improve, enhance, automate, and optimize systems and tools.
• Capacity to apply scientific analysis and mathematical modeling techniques to predict, measure and evaluate the consequences of designs and the ongoing success of our platform.
• Excellent oral and written communication skills.
• Bachelor’s degree or certification in Computer Science, Engineering, Mathematics, or any other related field.

Nice To Haves

• Proficient in multiple models and AI-related tools.
• Exposure to cloud infrastructure, such as Open Stack, Azure, GCP, or AWS as well as infrastructure management tech (Docker, Kubernetes)
• Relentless focus on scalability, latency, performance robustness, and cost trade-offs -- especially those present in highly virtualized, elastic, cloud-based environments.
• Hands-on expertise in many disparate technologies, typically ranging from front-end user interfaces through to back-end systems and all points in between.
• Familiarity with Machine Learning concepts & processes
• Masters or PhD in Computer Science, Physics, Engineering, Math, or equivalent.

Responsibilities

• Developing, testing and refining prompts for various applications, including text generation, question answering, data classification, and synthetic training data generation.
• Develop and maintain principled regression test suites in order to adequately measure and ensure prompt compliance at scale, for mission critical applications.
• Analyze and iterate on prompts, over time, based on performance metrics, user feedback and new product requirements.
• Collaborating with legal, product and data science teams to align prompts with overall company goals and compliance.
• Seamlessly navigate prompt characteristics of multiple model architectures (GPT, Llama, Gemini, our own fine-tuned LLMs) and versions (e.g. Llama2 vs. Llama 3).
• Creatively attack your own prompts, to assess safety exposure and strengthen their compliance characteristics.
• Continued research and education on the ever-changing AI field and emerging properties of large models.

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level