GenAI Developer (2 years Contract)

ST ENGINEERING IHQ PTE. LTD.; Singapore; Hybrid; SGD 90,000 - 120,000; Full time

Job summary

A technology and engineering firm is seeking a hands-on GenAI Developer in Singapore to design and productionize intelligent agentic systems powered by LLMs and computer vision. The ideal candidate will have over 6 years of software/AI development experience, with a strong focus on LLM applications and Python skills. This role offers a hybrid work setup and the opportunity to collaborate directly with top AI researchers in a low-bureaucracy, high-impact environment.

Benefits

Agile team environment

Direct collaboration with AI researchers

Opportunities for experimentation and self-development

Qualifications

• 6+ years in software/AI development, including 2+ years building LLM-driven applications.
• Hands-on experience with LLM APIs for prompt/tool workflows.
• Experience shipping AI tools or services into production.

Responsibilities

• Design and improve LLM-powered agents for task planning and execution.
• Build modular agent stacks using frameworks like LangChain and CrewAI.
• Lead prompt engineering and multi-agent coordination strategies.

Skills

Python

LLM APIs

Vector databases

Multi-agent orchestration

Tools

Docker

Kubernetes

OpenAI

FAISS

Pinecone

Job description

We’re looking for a hands‑on GenAI Developer to design and productionize intelligent agentic systems powered by LLMs, computer vision, and vector databases. You’ll build autonomous agents that reason, retrieve, and act - driving real‑world GenAI applications from prototype to production.

This is a true builder role for someone who enjoys taking ideas from notebooks to live users. You’ll work closely with Software and AI Engineers to integrate workflows into production and shape how our agents interact with tools, memory, data, and humans.

Key Responsibilities

• Design and improve LLM‑powered agents for task planning, execution, retrieval, and memory.
• Build modular agent stacks using frameworks like LangChain, CrewAI, AutoGen, or custom orchestrators.
• Develop workflows that connect agents to APIs, computer vision models, and vector databases.
• Lead prompt engineering, RAG pipelines, and multi‑agent coordination strategies.
• Collaborate with engineers to productionize agents with proper observability and debuggability.
• Evaluate agent behavior through logging, telemetry, and custom evaluation tools.
• Contribute to architecture patterns such as task workflows, tool interfaces, memory optimization, and feedback handling.
• Work with infrastructure teams to deploy agentic systems to production, ensuring monitoring, scaling, and rollback safety.
• Ensure compliance with Model Context Protocol (MCP) standards for structured context and execution.

Must‑Have Skills

• 6+ years in software/AI development, including 2+ years building LLM‑driven applications.
• Strong Python skills with experience in reusable agent stacks or RAG pipelines.
• Hands‑on with LLM APIs (OpenAI, Anthropic, HuggingFace, etc.) and building prompt/tool workflows.
• Experience integrating vector databases (Weaviate, FAISS, pgvector, Pinecone).
• Familiarity with multi‑agent orchestration (CrewAI, AutoGen, LangGraph, or custom).
• Experience shipping AI tools or services into production with containerization and cloud platforms (Docker, Kubernetes, GCP/AWS).
• Understanding of agent design (memory management, context management, tool contracts).
• Knowledge of Model Context Protocol (MCP) or similar standards.

Bonus Skills

• Experience with agent evaluation, prompt testing, and reducing hallucinations/latency.
• Exposure to hybrid workflows combining LLMs with computer vision.
• Knowledge of event‑driven or streaming agents (Kafka, LCEL, reactive frameworks).
• Experience building simple interfaces with Streamlit, Gradio, or browser automation.
• Familiarity with fine‑tuning techniques (LoRA/QLoRA) or multi‑modal agent training.

What We Offer

• Small, agile team (5–6 engineers + interns) with autonomy and real ownership.
• Startup feel with a big company resources: International environment where the majority of the team and leadership is from startups or big international corporations (Lazada, Gojek, IBM) and from various countries.
  Low‑bureaucracy, high‑impact startup environment where your code directly supports next‑gen AI deployment.
  Experimentation and self‑development are in our culture
  Knowledge sharing and collaboration
• Direct collaboration with top AI researchers and computer vision scientists.
• Hybrid work setup: ~2–3 days in office per week.