全职 Gen AI Engineer 工作, 薪水, Eames Consulting 公司招聘中 - Ricebowl

We are partnered with an established regional financial institution in Singapore that is scaling its enterprise AI engineering capabilities.

They are building out practical, high-impact generative AI applications and are looking for a Senior GenAI Application Engineer to sit at the intersection of core software engineering, enterprise integration, and LLM orchestration. This is not a prompt-tweaking or academic research role; it is an end-to-end engineering position focused on getting resilient, observable AI systems into production for enterprise users.

Key Responsibilities:

• Architect, ship, and scale robust GenAI applications using modern orchestration frameworks (e.g., LangGraph, LangChain) and custom agentic workflows.
• Build end-to-end Retrieval-Augmented Generation (RAG) pipelines, context management solutions, and structured tool-calling mechanisms integrated with enterprise systems and backend APIs.
• Implement production-grade engineering standards around LLM applications, including tracing, logging, automated evaluations, and defensive fallback patterns.
• Integrate open-weight models, hosted LLM endpoints, and specialized inference-serving patterns into core distributed architectures.
• Collaborate closely with cross-functional data, platform, infrastructure, and security teams to drive scalable, secure deployment across enterprise environments.

Requirements:

• 6+ years of core software engineering experience, with strong hands-on experience shipping GenAI applications into production (beyond demos, hackathons, or basic POCs).
• Deep experience with Python or Java, API design, and distributed backend resilience patterns.
• Demonstrated expertise in LangGraph, LangChain, RAG architectures, and agentic workflows.
• Practical exposure to observability, tracing, and logging for GenAI systems (e.g., Langfuse, Elastic).
• Experience with or solid interest in open-weight models and model-serving setups (e.g., vLLM).
• Familiarity with containerized deployments (Kubernetes, OpenShift) and state/cache management (e.g., Redis).
• Strong engineering discipline, high ownership, and the ability to challenge weak technical designs.