AI Engineer

SVM SOLUTIONS AND TECHNOLOGIES PTE. LTD.; Singapore; On-site; SGD 100,000 - 160,000; Full time

Job summary

Solverminds in Singapore is hiring an AI Engineer to build LLM-powered features and agents for maritime software products. Work with experienced AI engineers to move ideas from prototype to production, covering implementation, testing, deployment, and monitoring.

You will use LangChain/LangGraph, Python with FastAPI and Pydantic, and stay current with model developments. Collaboration with product and engineering teams is essential.

Qualifications

• Bachelor’s degree or equivalent practical experience.
• 2+ years software engineering in Python, incl. 1+ year building LLM-powered apps.
• Hands-on with FastAPI, Pydantic, async Python.
• Experience with LangChain/LangGraph or similar agent framework.
• Understanding of LLM basics and frontier/open-source models.
• Familiarity with agent design patterns (ReAct, planning, memory).
• Proficient communication with product and engineering teams.

Responsibilities

• Build and integrate LLM-powered features and agents.
• Implement and maintain evaluation tests for non-deterministic outputs.
• Take AI features from prototype to production, incl. testing, deployment, monitoring.
• Keep up with new models and agent tooling; share findings.
• Write clean, well-tested Python and participate in code reviews.
• Document designs, prompts, and evaluation results.

Skills

Python

LLM applications

LangChain/LangGraph

FastAPI

Pydantic

Async Python

Code testing

ML concepts (tokenization, context)

Communication with teams

Education

Bachelor’s degree in CS/SE or equivalent

Tools

LangChain

LangGraph

FastAPI

Pydantic

LangSmith

Langfuse

Job description

About the Role :

As an AI Engineer at Solverminds, you’ll build LLM-powered features and agents that bring AI

into our maritime software products, working with experienced AI engineers to take ideas from

prototype to production.

Responsibility:

• Build and integrate LLM-powered features and agents using LangChain/LangGraph,
• Implement and maintain evaluation and regression tests for non-deterministic LLM outputs, working with senior engineers on eval design.
• Take AI features from prototype to production, covering implementation, testing, deployment, and monitoring.
• Keep up with new models, agent frameworks, and tooling; run small experiments and share findings with the team.
• Write clean, maintainable, well-tested Python and take part in code review.
• Document system designs, prompt/context strategies, and evaluation results.

Required Skills & Experience :

• Bachelor’s degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience.
• A couple of years of professional software engineering experience in Python, including at least 1 year building LLM-powered applications.
• Hands-on experience with FastAPI, Pydantic, and async Python.
• Experience building with LangChain/LangGraph or a comparable agent framework.
• Working understanding of how LLMs work (tokenization, context windows, embeddings, transformer basics) and familiarity with both frontier and open-source models.
• Familiarity with common agent design patterns: ReAct, planning, reflection, tool use, memory, and multi-agent handoff.
• Daily use of AI coding assistants (e.g. Cursor, Claude Code).
• Clear communication and the ability to work with product and engineering teams.

Desired :

• MCP server/client integration; exposure to the A2A protocol.
• LLM testing and QA experience, including regression testing, red-teaming, and safety evaluation.
• Prompt and context engineering, and RAG pipeline design and optimization (chunking, retrieval, reranking, vector databases).
• Azure AI services (Azure AI Foundry, Prompt Flow, Azure OpenAI Service).
• LLM observability tools (e.g. LangSmith, Langfuse)