Garena

As an AI Applied Engineer, you will play a key role in maintaining and enhancing our existing AI and automation tools, developing new AI-driven solutions to boost efficiency, and collaborating closely with the game development team to bring innovative AI applications into our games. Job Description - Design and build scalable, modular, and production-grade AI architectures, including resilient orchestration layers, failover mechanisms, circuit breakers, and reusable AI services. - Develop and implement automated AI evaluation frameworks (e.g., LLM-as-a-judge, RAGAS, G-Eval, or custom metrics) to measure system quality, accuracy, relevance, and hallucination rates through data-driven KPIs. - Architect and optimize AI-powered systems capable of handling high concurrency, large-scale traffic, and terabyte-scale datasets with low-latency performance. - Drive AI cost optimization initiatives through engineering-led solutions such as semantic caching, intelligent model routing, prompt optimization, and token efficiency strategies. - Build and maintain robust AI data pipelines for large-scale ingestion, cleaning, embedding, vectorization, and efficient retrieval to ensure high-quality and up-to-date AI outputs. - Audit, improve, and productionize existing AI systems by identifying bottlenecks, improving scalability and reliability, and reducing hallucinations through continuous refinement and experimentation. - Implement enterprise-grade observability, monitoring, logging, and tracing systems to track AI performance, reliability, and cost efficiency in real time. - Write clean, maintainable, and scalable asynchronous Python code while applying strong software engineering principles, system design best practices, and design patterns. Job Requirements - Minimum 6+ years of experience in Software Engineering, with strong expertise in System Design and Distributed Systems, including 3+ years of hands-on experience building, deploying, and scaling LLM-based applications (RAG, AI Agents, Tool Use) in production environments. - Proven experience designing automated evaluation and monitoring pipelines to ensure AI system quality, reliability, and measurable performance. - Strong capability in optimizing LLM architecture for scalability and cost efficiency beyond prompt engineering approaches. - Hands-on expertise with modern AI and backend technology stacks, including Python (AsyncIO, FastAPI), Message Brokers (Kafka, RabbitMQ), Caching (Redis), Vector Databases (Pinecone, Milvus, Weaviate), Kubernetes, Docker, and CI/CD pipelines for AI workloads. - Strong problem-solving and project management skills, with the ability to translate ambiguous business challenges into scalable, production-ready technical solutions for high-concurrency and large-scale systems. - Demonstrated leadership experience in establishing engineering SOPs, technical standards, workflows, and mentoring or building teams with varying technical maturity levels. - Excellent communication and stakeholder management skills in both Bahasa Indonesia and English, with the ability to collaborate effectively across technical and non-technical teams. - Passionate about games and the gaming industry, with strong curiosity toward gaming products, player behavior, and industry best practices in Indonesia. - Willing to work under a 6-month contract with a full Work From Office (WFO) arrangement at our South Jakarta office.