Описание
Responsibilities Build and operate end-to-end ML and AI systems covering data preparation, model training, evaluation, inference, deployment, and production iteration. Develop production-grade AI infrastructure and backend services, including inference pipelines, orchestration layers, model-serving services, APIs, caching, batching, and streaming. Design and implement agentic AI workflows supporting multi-step planning, tool use, memory, failure handling, recovery, and integration with LLMs and external systems.
Monitor, debug, and optimize AI systems in production using logging, metrics, tracing, alerting, and production signals to improve latency, throughput, cost, reliability, and safety. Develop and integrate AI-powered product features across frontend, backend, ML, and AI systems, using production performance and usage data to drive continuous improvements.
Requirements
Strong production software engineering fundamentals, with experience building and operating high-throughput, low-latency backend services. Hands-on experience developing and deploying ML or AI systems, including model training, evaluation, inference, and production monitoring; experience with PyTorch . Experience with LLM-based systems and AI inference patterns, including OpenAI, Anthropic, or open-source LLMs , embeddings, tool calling, agent workflows, memory, or multimodal AI.
js , with experience using SQL and/or NoSQL databases , Docker , and Kubernetes . Experience debugging and optimizing distributed AI systems in production, including inference latency, throughput, caching, batching, streaming, observability, reliability, fallback mechanisms, and resource/cost optimization. GMP Recruitment Services (S) Pte Ltd | EA Licence: 09C3051 | VO UYEN AI LINH | Registration No: R22109232
Контакты работодателя (email/phone/telegram) скрыты из публичного превью —
отправьте резюме, чтобы мы связали вас напрямую.