Senior LLM Engineer

Confidential Jobs; Kuala Lumpur; On-site; MYR 180,000 - 240,000; Full time

Job summary

Confidential Jobs is seeking a Senior LLM Engineer to own GenAI-powered products from inception to production. You will balance building new features with improving existing apps, working directly with business stakeholders to turn ambiguous needs into working software.

You will navigate complex, inherited codebases, apply strong engineering judgment, and drive quality across architecture, testing, and documentation in an enterprise yet startup-minded environment.

Qualifications

• 7+ years of hands-on full-stack or product engineering experience shipping and supporting production applications.
• Strong across the stack: frontend, backend, APIs, databases, auth, and integrations.
• Strong debugging and root-cause analysis, including in messy or poorly documented codebases.
• Practical experience with AI coding tools, and the judgment to tell when their output is wrong, unsafe, or fragile.
• Comfortable with cloud, containers, CI/CD, and basic observability.
• Ownership mindset: a self-starter who defines their own work, drives it to done, and doesn't need close management.
• Maturity with ambiguity: comfortable navigating competing stakeholders, unclear requirements, and organizational messiness.
• Good written and verbal English, with technical and non-technical people.

Responsibilities

• Work directly with business stakeholders to scope, prioritize, and deliver — translating needs into requirements yourself rather than waiting for a spec.
• Build new GenAI/LLM features and applications, and the APIs and services that integrate them with internal systems.
• Take over existing applications: inspect, debug, validate AI-generated code, and fix correctness, security, and performance issues.
• Standardize quality, architecture, testing, and documentation across inconsistent codebases.
• Use AI coding tools to move faster, while applying your own engineering judgment on what to trust.
• Improve the team's prompting, tooling, and QA practices for AI-assisted development.
• Write clear documentation: architecture notes, setup guides, runbooks, handover materials.

Skills

Full-stack engineering

Frontend & Backend

APIs & Databases

Debugging & root-cause analysis

English communication

Ownership mindset

Tools

Claude Code

Cursor

AWS

Docker

CI/CD tooling

Job description

We're looking for a versatile Senior LLM Engineer to build and own GenAI-powered products end-to-end. This is a forward-deployed, product-minded role: you'll work directly with business stakeholders — often without a product or project manager in between — to turn ambiguous needs into working software.

The work is an even split between building new LLM-powered features and applications, and taking ownership of existing digital apps built by various contributors (including AI-assisted codebases) — hardening, debugging, and improving them. You should be comfortable both starting from a blank page and working in inconsistent, inherited systems.

We're an enterprise environment, but we want an early-stage-startup mindset: you take strong ownership, move without waiting to be told, communicate clearly, and drive work to done. If you pair the maturity to navigate ambiguity, stakeholders, and messy systems with the drive to own outcomes end-to-end, this role is for you.

What you'll do

• Work directly with business stakeholders to scope, prioritize, and deliver — translating needs into requirements yourself rather than waiting for a spec
• Build new GenAI/LLM features and applications, and the APIs and services that integrate them with internal systems
• Take over existing applications: inspect, debug, validate AI-generated code, and fix correctness, security, and performance issues
• Standardize quality, architecture, testing, and documentation across inconsistent codebases
• Use AI coding tools (e.g. Claude Code, Cursor) to move faster, while applying your own engineering judgment on what to trust
• Improve the team's prompting, tooling, and QA practices for AI-assisted development
• Write clear documentation: architecture notes, setup guides, runbooks, handover materials

Requirements

• 7+ years of hands-on full-stack or product engineering experience, shipping and supporting production applications
• Strong across the stack: frontend, backend, APIs, databases, auth, and integrations
• Strong debugging and root-cause analysis, including in messy or poorly documented codebases
• Practical experience with AI coding tools, and the judgment to tell when their output is wrong, unsafe, or fragile
• Comfortable with cloud, containers, CI/CD, and basic observability
• Ownership mindset: a self-starter who defines their own work, drives it to done, and doesn't need close management
• Maturity with ambiguity: comfortable navigating competing stakeholders, unclear requirements, and organizational messiness — the kind of judgment that comes from enterprise, consulting, or startup environments
• Good written and verbal English, with technical and non-technical people

Most Preferred Stack: Python and/or Node/TypeScript backends, React frontend, AWS and Docker

Nice to have

• Experience building LLM-powered features (RAG, agents, document workflows, structured extraction)
• Experience taking over apps built by agencies, vendors, or distributed contributors
• Experience raising engineering standards or building internal tooling across multiple apps
• Background spanning both enterprise/consulting and early-stage startups