SEA Limited Hiring! Full Time AI Engineer in - Ricebowl

Spark is an enterprise AI assistant embedded in our communication suites. It helps employees understand conversations, access workplace knowledge, communicate effectively, and complete tasks across enterprise tools.

We are looking for an AI Engineer to build and operate production-grade AI Agent capabilities for Spark. You will work across LLM orchestration, backend services, enterprise integrations, memory and evaluation systems, owning features from design through production deployment.

As part of the Spark AI Engineering team, you will:

• Design, build, and deploy LLM-powered applications and AI agents
• End to end product delivery, experimenting with different models, frameworks, and approaches to identify the best solution for specific product and business requirements.
• Develop AI workflows using techniques such as RAG, tool calling, function calling, agentic workflows, and prompt engineering.
• Collaborate closely with Product Managers and Designers to translate user needs into practical AI solutions.
• Prototype and iterate quickly, using experiments and user feedback to validate ideas before productionising them.
• Optimise AI systems for accuracy, scalability, latency, and cost.
• Take ownership of deploying and maintaining AI solutions in production, including monitoring performance and continuously improving the system.
• Stay up to date with developments in LLMs, generative AI, and AI agent technologies, and identify opportunities to apply emerging techniques to our products.

Requirements:

• Bachelor’s degree and above in Computer Science, Artificial Intelligence, Computer Engineering, Data Science or a related field.
• Relevant full time or internship experience in AI/LLM engineering roles
• Strong programming skills in Python
• Hands-on experience building applications using LLMs or Generative AI.
• Hands-on experience with RAG architectures and frameworks such as LangChain or LangGraph
• Familiarity with APIs, databases, cloud platforms, and deploying applications to production.
• Strong problem-solving skills and the ability to evaluate technical trade-offs between quality, cost, latency, and complexity.
• Comfortable working in a fast-moving environment where requirements and AI technologies evolve rapidly.