The posting
About Vinova
Vinova is a Singapore-headquartered software development company that builds web, mobile, and enterprise applications. Our engineers work with clients and cross-functional teams to design, deliver, and operate software that solves real business problems.
Role Overview
We're looking for a hands-on AI Engineer to build and ship LLM-powered features and agentic workflows. You'll work with the AI Engineering Lead, product teams, and software engineers to turn use cases into working prototypes, evaluate their performance, and deploy them to production on AWS or Microsoft Azure.
You'll integrate models such as Claude and Grok where they fit the use case and use coding agents such as Codex and Claude Code to support day-to-day engineering. You'll review generated code and verify its behavior through testing before it ships.
Key Responsibilities
- Build AI-powered features and agentic workflows that use structured outputs, call tools, and integrate with existing APIs and data sources.
- Prototype and compare models, prompts, and workflows against task accuracy, latency, and cost. Document the results so the team can make informed implementation decisions.
- Build evaluation datasets and automated checks for model outputs and agent behavior. Handle invalid outputs, tool failures, and cases that require human review.
- Deploy and maintain AI services on AWS or Azure. Contribute to CI/CD pipelines, application monitoring, and production troubleshooting.
- Use coding agents to explore codebases, implement changes, and write tests. Review generated code for correctness, security, and maintainability.
- Collaborate with product and engineering teams to clarify requirements, share progress, and improve features based on user feedback and production data.
What You'll Bring
- Hands-on software engineering experience in Python, TypeScript, C#, or another backend language, including building APIs and integrating external services.
- Experience building at least one LLM-powered application or agentic workflow. Ability to explain what you implemented, how you tested it, and how you handled failures.
- Familiarity with LLM APIs, structured outputs, tool calling, and evaluation techniques.
- Experience deploying or supporting applications on AWS or Azure, with familiarity with Git, CI/CD, and application monitoring.
- Practical experience using Codex, Claude Code, or a comparable coding agent. Ability to scope a task, review the resulting changes, and verify the outcome.
- Ability to communicate technical decisions and work effectively with engineering and product teams in English.
Nice to Have
- Experience with Amazon Bedrock, Azure AI Foundry, or model APIs from providers such as Anthropic or xAI.
- Experience with retrieval-augmented generation (RAG), vector search, Model Context Protocol (MCP), or multi-step agent orchestration.
- Experience monitoring production AI features for task success, tool failures, latency, and cost.
What We Offer
- Competitive compensation and performance-based incentives.
- Flexible working hours subject to project requirements.
- Opportunities to work directly with international clients and collaborate with product, design, and engineering teams across regions.
- Opportunities for short- and long-term onsite assignments in Singapore.
- Team-building activities and an annual company trip.



