Search by job, company or skills

4-6 Years
Not Disclosed
  • Posted 6 hours ago
  • Be among the first 10 applicants

Job Description

About the Opportunity

Our client, the AI arm of a leading Real Estate Group is among the first to put AI agents into live property operations. Its platform is already in live use across a large residential portfolio, drawing on years of proprietary operational data that few competitors could replicate. The business is now seeking an AI Agent Engineer to join its core team in Singapore. This is AI doing real work in production. Join the pioneering team to have a visible impact on the product from the outset.

This is a friendly, welcoming and down-to-earth team that values collaboration, with a hybrid working arrangement.

Responsibilities

At the centre of this role is the design and delivery of conversational AI agents that residents and property teams rely on every day. You will own features end to end, working across prompt design, tool calling, retrieval and conversational flow, through to the Java backend services and the dashboard that support them. The platform is expanding from its current feature set to something considerably broader, and you will play a real part in how it grows. The role carries genuine autonomy, close working relationships with product and operations colleagues, and a team that treats modern AI coding tools as part of everyday engineering.

Requirements

This will suit an engineer with around four or more years of software engineering experience who has shipped LLM features to real users, including tool calling and retrieval-augmented generation, rather than prototypes or internal demos. You bring solid experience with at least one agent framework and with vector search, and you understand what breaks when AI runs in production and how to put it right. Strong backend fundamentals are essential, covering API design, relational databases and running production systems, and you are comfortable working in Java daily, as the platform and its agents are built on it. Experience with Spring Boot is an advantage, though strong Java engineers will pick it up quickly. Above all, you take ownership, can turn a product requirement into a working feature without close supervision, and communicate clearly with a distributed team to see it through.

To Apply

Interested candidates are invited to apply in confidence, quoting the role title. Only shortlisted candidates will be notified.

Reg. No. R1550844

More Info

Job Type:
Industry:
Function:
Employment Type:

Key Skills

vector search

LLM features

tool calling

agent framework

retrieval-augmented generation

Similar Jobs

3-6 yrs
SGD 12,000 - 24,000 per month
Singapore
Skills:
Retrieval-Augmented Generation (RAG), Large Language Models (LLMs), Data Analysis, AI-powered capabilities, Memory Mechanism and Evaluation Iteration, Data inspection and attribution, anomaly detection, Agent technology ecosystem, Performance Analysis, Automation of experimental analysis, Prompt Engineering, Function Calling, Observability
2-4 yrs
Singapore
Skills:
Orchestration, Python, embedding fine-tuning, tool calling, recall ranking, fine-tuning LLMs via SFT and DPO, RAG retrieval systems, multi-agent LLM systems, task planning
2-5 yrs
SGD 9,000 - 12,000 per month
Singapore
Skills:
Python, embedding fine-tuning, SFT, owl, DPO, RAG retrieval systems, task planning, AutoGen, LangGraph, recall ranking, Agent frameworks, orchestration tool calling, multi-agent LLM systems, fine-tuning LLMs, Google Agent Development Kit
4-6 yrs
Singapore
Skills:
alerting), Production observability (logging, API design, React, Typescript, FastAPI, Python, tracing, Evaluation harnesses, code generation, AWS architecture, Retries and idempotency, Go, SGLang, Infrastructure-as-code, vLLM, Ollama, CI/CD pipelines, Error handling, Asynchronous frameworks, Agentic development
2-5 yrs
SGD 8,000 - 10,000 per month
Singapore
Skills:
Databases, Apis, Python Programming, embeddings, RAG architecture, tool calling, open-source LLMs, vector databases, agent workflows, prompt engineering, retrieval systems, Evaluation, LLM APIs, retrieval strategies, hallucination mitigation, backend integration, semantic search, function calling