Senior LLM Systems Engineer — Production AI & Agents

Xora Innovation; Singapore; Hybrid; SGD 120,000 - 180,000; Full time

Job summary

ELEMYNT, part of Xora Innovation, seeks an experienced engineer to own the LLM systems powering our platform. You will build, evaluate, and deploy production-grade agents and fine-tuned models, ensuring reliability whether self-hosted or via commercial APIs.

The role spans model internals to shipped software in secure environments. The ideal candidate has strong Python, hands-on LLM experience, and a track record with RAG, prompts, and tool integration.

Qualifications

• 5+ years building production software with LLM-powered systems
• Strong Python and reliable service delivery (async, HTTP, streaming)
• Experience with prompting, context engineering, and tool usage for LLMs

Responsibilities

• Build end-to-end LLM-powered capabilities and production services
• Design multi-step agents with tool calls, structured outputs and state
• Develop retrieval with embeddings, chunking, and hybrid search
• Fine-tune open-weight models (LoRA/QLoRA) on multi-GPU and curate data
• Create evaluation loops with automated scoring, & tracing for production
• Instrument model calls and tooling with tracing for debuggability
• Expose LLM capabilities as clean APIs for other engineers

Skills

Python

LLM systems

Async APIs

Tool calling

Agents design

Vector embeddings

RAG systems

LangGraph

Education

Bachelor's or Master's in CS/Engineering

Tools

LoRA/QLoRA

Open-weight models

vLLM/TGI/SGLang

Retrieval systems

Job description

ELEMYNT, part of Xora Innovation, seeks an experienced engineer to own the LLM systems powering our platform. You will build, evaluate, and deploy production-grade agents and fine-tuned models, ensuring reliability whether self-hosted or via commercial APIs.

The role spans model internals to shipped software in secure environments. The ideal candidate has strong Python, hands-on LLM experience, and a track record with RAG, prompts, and tool integration.