AI Engineer

About the Team

Spark is an enterprise AI assistant integrated within our communication suites, designed to help employees interpret conversations, retrieve workplace knowledge, communicate effectively, and execute tasks across various enterprise tools.

Role Overview

We are seeking an AI Engineer to develop and manage production-ready AI Agent functionalities for Spark. This role involves working on large language model (LLM) orchestration, backend services, enterprise integrations, memory, and evaluation systems, overseeing features from conceptualization to deployment.

Responsibilities

• Architect, develop, and launch applications and AI agents powered by LLMs.
• Deliver complete product cycles by experimenting with multiple models, frameworks, and methodologies to find optimal solutions aligned with product and business needs.
• Create AI workflows leveraging methods such as Retrieval-Augmented Generation (RAG), tool and function calling, agentic workflows, and prompt engineering.
• Partner closely with Product Managers and Designers to convert user requirements into viable AI implementations.
• Rapidly prototype and iterate through experiments and user feedback, validating concepts prior to production deployment.
• Enhance AI systems focusing on improving accuracy, scalability, latency, and cost efficiency.
• Oversee deployment and ongoing maintenance of AI solutions in production environments, including performance monitoring and continuous enhancement.
• Keep abreast of the latest developments in LLMs, generative AI, and AI agent technologies and explore ways to incorporate cutting-edge techniques into products.

Requirements

• Bachelor’s degree or higher in Computer Science, Artificial Intelligence, Computer Engineering, Data Science, or related disciplines.
• Proven full-time or internship experience in AI or LLM engineering roles.
• Advanced programming proficiency in Python.
• Practical experience developing applications with LLMs or generative AI technologies.
• Hands-on knowledge of Retrieval-Augmented Generation (RAG) architectures and frameworks such as LangChain or LangGraph.
• Familiarity with APIs, databases, cloud platforms, and deploying software to production environments.
• Strong analytical and problem-solving abilities with skill in balancing technical trade-offs involving quality, cost, latency, and complexity.
• Adaptability to thrive in a dynamic environment with rapidly evolving requirements and AI technologies.