Senior AI Engineer - Quality Platform

Crane Venture Partners; Bengaluru; On-site; INR 4,000,000 - 7,000,000; Full time

Job summary

Aspire is building the financial operating system for global founders, bringing banking, software, and automation into a single platform so businesses can move faster across borders. We are hiring a software engineer who builds AI systems to raise quality automatically across Aspire's engineering organization.

You will design, build, and ship tooling for test generation, merge guardrails, and AI-assisted code reviews in a regulated fintech environment.

Qualifications

• Proven experience shipping AI systems and LLM-based tooling.
• Strong software engineering with a quality mindset and production-grade coding.
• Ownership, data-driven decision making, and initiative.
• Experience in fintech or regulated environments is a plus.

Responsibilities

• Build and productionize AI test generation pipeline from specs to tests.
• Improve guardrails to scale across engineering tribes and integrate with pipelines.
• Develop automation tooling including synthetic data, AI agents and failure classification.
• Collaborate with QA to embed AI-assisted quality practices.

Skills

AI systems

TypeScript

Python

LLM applications

Prompt engineering

RAG retrieval

Agent tooling

QA automation

Fintech domain

Ownership & initiative

Tools

Playwright

GitHub Actions

Jenkins

Job description

About The Company

Founders today are building global companies from day one — but the systems that manage their money were built for a different era. Aspire exists to change that! We’re building the financial operating system for global founders, bringing banking, software, and automation into a single platform so businesses can move faster across borders and stay focused on building. Aspire is built by people who think from first principles, care deeply about solving hard problems, and take real ownership of their work. Our team brings global experience from leading fintech and technology companies, and many of us are former founders and operators who understand what it takes to build thoughtfully, make trade-offs, and deliver at scale in a global environment. Backed by leading global investors including Y Combinator, Peak XV, and Lightspeed, Aspire has been trusted by more than 50,000 startups and growing businesses worldwide to manage their finances since 2018. Together with partners like J.P. Morgan, Visa, and Wise, we’re building for the next generation of global companies.

About The Role

Software quality and code volume are increasingly an engineering and AI problem. Leading teams now use agents to generate tests, detect coverage gaps before merge, and enforce quality through infrastructure rather than manual processes. At Aspire, we're already building this infrastructure. We have a merge guardrail in production that reads live product specs and blocks PRs when coverage gaps are detected. We are building an LLM pipeline that generates tests directly from specs, and a live traceability matrix that keeps specs, code, and test results in sync, along with AI-assisted code review. We are hiring a software engineer who builds AI systems and has a strong understanding of coding, testing and quality. You will design, build, and ship the AI tooling that makes quality automatic across Aspire's engineering organisation.

What You'll Own

• The AI test generation pipeline. Build the LLM system that assesses product specs for gaps and testability, and converts them into automated tests. You will take it from POC to production, owning context retrieval across specs and codebases, prompt and agent design, evaluation frameworks for generation accuracy, and feedback loops based on live test results.
• The merge guardrail. The guardrail is live and blocks merges when coverage is missing or critical bugs are detected. You will improve its precision, scale it across all engineering tribes, and integrate it with the generation pipeline so it creates missing tests rather than only blocking for them.
• Reliable automation tooling. Build the intelligence layer behind our automation, including synthetic test data generation, AI agents that explore and verify flows, automated failure classification, and risk-based test selection, so that every alert is accurate and actionable.
• Quality platform ownership. Understand the spec, the code, and the failure modes, and build that understanding into systems. Contribute at the design stage, not after release. In a regulated fintech serving 50,000+ businesses, quality gaps directly impact customers. Work closely with QA engineers to embed AI-assisted practices and use quality data (coverage, escape rates, flakiness) to drive decisions.
• Security regression in CI. Design and build automated security regression tests for our highest-risk API endpoints, ensuring every auth boundary is verified at merge. This is a MAS Singapore requirement and will be built from scratch.

What We're Looking For

• Proven experience shipping AI systems. You have built and deployed an LLM application, agent, developer tool, or automation that replaced real manual work. You understand common failure modes such as hallucinations, context limits, and evaluation gaps, and how to address them.
• Strong software engineering with a quality mindset. You write production code, design systems, and build tools used by other engineers. You understand test architecture, coverage, and failure analysis well enough to define what good testing looks like.
• High standards. You address root causes rather than symptoms and treat production defects and flaky tests as system-level problems to eliminate.
• Ownership and initiative. You identify problems, validate them with data, and propose solutions without waiting to be assigned.
• Comfort with ambiguity. You are motivated by an evolving roadmap that starts with quality and extends to wider engineering workflows as we learn what works, and you want to help shape its direction.

Technical Skills

• Strong software engineering in TypeScript and/or Python, with experience building production services, internal tools, or developer platforms
• Hands-on experience building LLM applications, including prompt engineering, RAG or context retrieval, agents or tool use, and output evaluation. Side projects, internal tools, or POCs count if they were shipped.
• Strong day-to-day use of AI coding tools and agentic workflows.
• Solid understanding of test automation and test architecture; Playwright experience is a strong plus
• CI/CD experience (GitHub Actions, Jenkins), including building tooling that integrates at PR and merge stages
• Ability to read and reason about backend code, API contracts, and service boundaries
• 5+ years in software engineering with meaningful exposure to development, testing, quality, or developer tooling, preferably including a fintech or regulated-environment project
• Experience owning a system or product domain end-to-end
• Familiarity with financial workflows such as payments, KYB/KYC, and transaction processing is a strong plus

What This Role Is NOT

• Building AI prototypes that never reach production.
• Waiting at the end of the delivery pipeline for a build.
• Maintaining a regression suite without evaluating its value.
• Treating quality as another team's responsibility.

In Your First 90 Days, You'll Probably

• Become the go-to engineer for building quality into development workflows.
• Challenge at least one existing practice with data and propose a better approach.
• Review the codebase and identify the three biggest quality gaps based on data, propose solutions, and build tooling for at least one.
• Deliver a measurable improvement in quality via the test-generation pipeline, the merge guardrail, automation reliability, code review etc.