Senior QA Engineer / SDET

Company Description

Straitpoint is an AI-driven business and technology company dedicated to designing, building, and operating modern digital systems. The company develops proprietary platforms and partners with organizations to address critical business and technology challenges. In this project, we are creating an agentic AI-powered children's storytelling app.

About the Role

Quality at an agentic AI startup is not just about whether buttons work. It is about whether AI behaves.

As our Senior QA / SDET, you will own the entire quality engineering function for a platform where the output is dynamically generated stories, real-time audio, and AI-driven interactions experienced by children ages 26.

You will build intelligent test systems that evaluate not just code correctness, but AI output quality, safety, and consistency.

This role is for someone who thinks like an engineer, tests like a detective, and embraces AI as both the product being tested and the tool used for testing.

Key Responsibilities

Test Architecture & Automation

Design and own the end-to-end test automation strategy across mobile (Flutter / iOS), backend services, and AI pipelines

Build robust, maintainable test frameworks from the ground up using modern SDET practices

Develop automated regression, integration, and performance test suites integrated into CI/CD pipelines

Maintain test environments that mirror production, including on-device AI model behavior

AI & LLM Quality Engineering

Design evaluation frameworks for LLM-generated story content, assessing coherence, age-appropriateness, safety, and engagement quality

Build automated pipelines that run LLM outputs through scoring rubrics, safety classifiers, and regression benchmarks

Detect and track AI-specific failure modes such as hallucinations, prompt injection vulnerabilities, inconsistent persona behavior, and content policy violations

Collaborate with AI engineers to define measurable quality thresholds for model updates and prompt changes

Test agentic workflows end-to-end, including multi-step LLM chains, tool-calling sequences, and cross-session context management

Mobile & Platform QA

Own test coverage for the iPad-first Flutter application across device types, OS versions, and edge cases

Test on-device AI model integration (Apple Intelligence / Core ML), including offline scenarios, memory constraints, and model fallback behavior

Validate audio playback, TTS synchronization, and interactive media features across varying network conditions

Ensure builds meet App Store submission and review standards

Child Safety & Compliance Testing

Develop specialized test protocols for child-facing AI content, including adversarial prompt testing and edge-case content scenarios

Validate COPPA and GDPR-K compliance in data handling, consent flows, and parental management features

Conduct structured red-teaming exercises targeting child safety guardrails in the AI content pipeline

Quality Culture & Process

Define and track quality KPIs across engineering, including defect escape rate, test coverage, eval pass rates, and incident metrics

Embed quality gates into CI/CD workflows and enforce them as deployment blockers

Mentor junior engineers on testing best practices and AI-aware quality thinking

Produce clear, well-documented bug reports and drive issues to resolution with product and engineering

Requirements

Must Have

5+ years in QA engineering or SDET roles, with at least 2 years in a senior or lead capacity

Strong programming skills in Python, Dart, TypeScript, or similar. You write code, not just test scripts

Proven experience building test automation frameworks from scratch

Hands-on experience with mobile testing, iOS or Flutter preferred

Solid understanding of CI/CD integration and writing reliable automated tests

Active use of AI tools in daily engineering workflows

Strong debugging and root cause analysis skills across complex systems

Nice to Have

Direct experience writing LLM evals or working with evaluation frameworks (LangSmith, RAGAS, PromptFoo, or custom-built)

Familiarity with AI safety concepts such as content moderation, output filtering, prompt injection, and jailbreak testing

Experience testing on-device ML models or Core ML integrations on Apple platforms

Background in testing audio or real-time interactive applications

Knowledge of child safety standards in digital products, including COPPA and GDPR-K

Experience in early-stage startups where quality infrastructure was built from zero

Technical Stack You'll Work With

Mobile: Flutter, iOS (Swift / SwiftUI), TestFlight

AI / LLM: Anthropic Claude, Apple Intelligence (on-device), Core ML

Backend: Node.js / TypeScript services, REST and streaming APIs

CI/CD: GitHub Actions

Cloud: AWS

Testing Tools: Your recommendations will help shape our stack

The Mindset We're Hiring For

You treat AI outputs as first-class test subjects, not black boxes

You are proactive and anticipate failure modes before they ship

You are comfortable owning quality end-to-end in a fast-moving environment

You recognize the responsibility of building for toddlers and young children

You use AI to write better tests and automate repetitive QA work without cutting corners

You document what you build so the team can sustain it

What Success Looks Like in 90 Days

By the end of your first 90 days, you will have:

Audited the existing test coverage

Shipped at least one automated eval pipeline for AI story content

Integrated quality gates into CI/CD

Produced a clear testing roadmap for the next two quarters

Why Join Straitpoint

• You will help define how AI-powered systems are validated, monitored, and deployed at scale.
• You will work closely with experienced technical leadership and contribute to architecture-level decisions.
• This role has long-term growth potential.

Location: Sudirman, CBD, Jakarta

Work Model: Full-Time, WFO

Apply via LinkedIn or send your CV to: [Confidential Information]