Junior / Senior Software Engineer

Location: Kuala Lumpur / Hybrid (Malaysia)

Type: Full-time

Apply: [Confidential Information]

About Pantas

Pantas is an AI-first software company helping businesses measure, manage, and reduce their carbon emissions and ESG risks. We work with leading financial institutions and corporates across Southeast Asia to turn complex climate data into decisions that matter.

But Pantas is not only an ESG and climate software company. Alongside our core platform, we are building and preparing to launch a new GenAI agentic product line in stealth mode — an AI-native product that goes beyond traditional ESG software. We can't share details publicly yet, but the engineers we hire today will help shape it.

What Makes Engineering at Pantas Different

A lot of companies call themselves AI-first. Here is what that actually means at Pantas.

You'll work directly with a technical founder who codes.

Our CEO is a technical founder who leads our engineering direction and AI development. He codes, runs monthly AI deep-dive workshops, and is in the room when we make hard engineering and product decisions. Topics he leads include advanced prompting, AI agents, vector embeddings, and the full stack of context, harness, intent, and spec engineering. AI isn't a separate team here — it is the default way everyone works, including non-technical roles.

Best-in-class AI engineering tooling, by default.

Claude Code, OpenAI Codex, and Gemini CLI are part of the default engineering stack, alongside other agentic and AI coding tools we add as the ecosystem evolves. You'll work across both frontier and open-source models (GPT, Claude, Gemini, DeepSeek, Qwen, Kimi, GLM) and modern AI infrastructure (Databricks, Hugging Face, OpenRouter, Unsloth, AWS SageMaker, Google Vertex AI).

You will build AI-native systems, not only CRUD software.

You'll still ship reliable production software for our ESG and climate platform — clean APIs, solid data pipelines, secure integrations. But the opportunity is broader. You'll also work on LLM-powered features, agentic workflows, simulation and scenario analysis, internal AI infrastructure, and our stealth-mode GenAI agentic product.

You'll learn the engineering disciplines behind agentic systems.

Hands-on practice in:

• Prompt engineering — getting reliable behaviour out of models.
• Context engineering — structuring the right information and memory so agents produce high-quality output.
• Harness engineering — building the guardrails, toolchains, and orchestration that let agents operate reliably at scale.
• Intent and spec engineering — translating business intent into specs that humans and agents can both execute against.
• Agentic coding workflows — internal infrastructure that compresses the distance between idea and shipped feature.

Where relevant, engineers also experiment with model fine-tuning, autoresearch-style workflows, and other emerging LLM techniques.

We experiment constantly.

Persistent memory (second brain) systems for AI, end-to-end AI testing/QA agents, Claude Design for design-to-code, AI PRD agents that turn product ideas into structured specs, internal agentic coding harnesses — we are always testing new ways to ship faster and better. For engineers who want it, this is a credible path to grow from software engineering toward AI engineering.

The Role

As a Junior / Senior Software Engineer, you will help design and build the next generation of Pantas climate and ESG platform, our generative AI agent features, and our stealth-mode GenAI agentic product line. You'll own meaningful parts of our backend and/or full-stack systems, work closely with product, business analysts, and data science, and help shape how AI tools and workflows are used across the engineering team.

What You'll Do

• Design, build, and maintain scalable backend and/or full-stack services for our ESG and climate platform and our AI agent products.
• Contribute to the development of Pantas stealth-mode GenAI agentic product, respecting product confidentiality at every step.
• Turn AI-generated PRDs and implementation plans into secure, robust, production-grade systems.
• Integrate with external systems (banks, partners, customer data sources) and ensure data is clean, consistent, and auditable.
• Build LLM-powered features and agentic workflows — orchestration, tool-use, retrieval, evaluations, and modern AI infrastructure.
• Apply prompt, context, harness, intent, and spec engineering to ship features that are both fast to build and reliable in production.
• Design and improve internal agentic coding infrastructure that speeds up the entire engineering team.
• Contribute to system architecture, coding standards, and our internal AI engineering playbook.
• Mentor other engineers in using AI tools effectively.

What You'll Need

• Minimum of 1 year as a software engineer in backend or full-stack roles, comfortable owning features end-to-end.
• Strong skills in at least one modern backend stack (e.g. Python/Django, Node.js) and experience with SQL databases.
• Experience building web applications or APIs in production.
• Comfort working in a fast-moving startup: shipping iteratively, handling ambiguity, and collaborating closely with non-engineering teammates.
• An AI-native mindset — you treat AI as part of your engineering stack, not a novelty. You are already using (or keen to master) tools like Claude Code, OpenAI Codex, and Gemini CLI.

Great If You Also Have

• Experience mentoring engineers or shaping engineering practices on a team.
• Exposure to cloud platforms (AWS/GCP/Azure) and data/ML infrastructure.
• Experience building or integrating LLM-powered features (MCP, prompt orchestration, agentic workflows, retrieval, evaluations).
• Familiarity with context, harness, intent, or spec engineering in real systems.
• Hands-on experiments with model fine-tuning, autoresearch-style workflows, or other emerging LLM techniques.

Show Us What You've Built With AI

We want to see how you think with AI, not just how you talk about it. In your application, please share any AI experiments, prototypes, agents, fine-tuning work, automations, prompt or context workflows, internal tools, or side projects that show your curiosity. A short write-up, a repo link, a demo video, or a screenshot is enough. Polish is not the point — signal is.

What We Offer

• The chance to build meaningful software that helps businesses decarbonise and access sustainable finance — alongside cutting-edge AI agent products.
• A hybrid, flexible work environment based in Kuala Lumpur, Malaysia.
• Direct access to a technical founder who codes alongside the team and leads our engineering and AI direction.
• Monthly AI deep-dive workshops led by the CEO, plus a culture that genuinely rewards experimentation.
• Competitive salary, ESOP, and a learning-heavy environment where you grow as both a senior engineer and an AI practitioner.

We celebrate diversity and are proud to be an equal opportunity employer. We do not discriminate on the basis of race, religion, colour, national origin, gender, age, marital status, sexual orientation, or disability status.

If you are a senior engineer who wants to build real products, in a real market, with AI at the centre of how you work — we'd love to hear from you.