Evaluation Engineer Intern

Department: Platform Engineering

Qualification: B.Tech / B.E. / B.Sc. in Computer Science, Information Technology, or a related discipline Experience: Freshers (2026 & 2025 Graduates only)

Work Location: Bangalore (Sattva Global City)

Work Model: Work from Office

About Aura Cloud

Aura Cloud is an AI-embedded, cloud-native core banking platform. API-first and cloud-agnostic, the Aura platform spans Loans, Deposits, Cards, Payments and more, with multi-currency and multi-entity support for global scalability. Over 2,000 APIs, ISO 27001 and ISO 9001 certified, and trusted by financial institutions to run and grow their core business.

We are embedding AI across the platform — in how it's built, how it's evaluated, and increasingly in how it operates. That changes what software quality means, and it's why this role exists.

Role Overview

We are looking for curious, analytical, AI-oriented Evaluation Engineers to evaluate features across our AI-embedded banking platform. You'll turn requirements into evaluation scenarios, define what correct looks like, exercise the platform against it, and analyse results to establish functionality, accuracy and reliability — using AI tools throughout to design scenarios, generate data and extend coverage.

As more of the platform becomes agentic, so does the scope of this role — and the engineers who know the platform best will be the ones defining how we evaluate it.

The ideal candidate has a genuine interest in AI-assisted development of software, and correctness as a problem worth solving.

Key Responsibilities

• AI Evaluation Frameworks: Build AI-based frameworks for evaluation of AI-generated code.
• AI-Assisted Scenario Design: Use AI tools to design use cases, evaluation scenarios and workflows for validating platform features.
• Feature Evaluation: Understand platform requirements and evaluate whether new features meet them.
• Analysis — Run evaluation scenarios, compare actual against expected outcomes, and identify gaps, inconsistencies and failure modes.
• AI Tool Utilisation — Generate scenarios and data, automate and improve coverage and speed.
• Failure Analysis — Diagnose failures to the point of knowing what broke and why; classify failure modes, document them, and drive issues to closure.
• Evaluation Automation — Build the harnesses and pipelines that operate repeatably and at scale.
• Documentation — Maintain clear records of use cases, evaluation criteria, results, observations and issues.
• Cross-Functional Collaboration — Work closely with Engineering through the feature lifecycle.
• Continuous Improvement — Explore new AI tools, evaluation techniques and methodologies to strengthen coverage and effectiveness.

Required Skills & Qualifications

• B.Tech / B.E. / B.Sc. (2026 & 2025 batches) in Computer Science, Information Technology, or a related discipline.
• Working knowledge of generative AI tools, Large Language Models, backed by project work on GitHub.
• Sound grasp of software development concepts, programming fundamentals and evaluation principles.
• Working ability in at least one language — Python, JavaScript, to call an API, parse the response and assert something about it.
• Strong analytical and logical reasoning, with the ability to identify patterns, inconsistencies and likely failure scenarios.
• The instinct to ask "how would I know if this were wrong?"
• Clear written and verbal communication, with attention to detail and a structured approach to documentation.
• Willingness to learn quickly and work in a fast-paced product

Preferred / Good-to-Have Skills

• Using AI tools to design evaluation scenarios, generate data, and assess software output.
• Automating repeatable checks, debugging, and working with Git.
• REST APIs, JSON, SQL and database fundamentals.
• Reasoning about coverage: functional, regression and edge-case scenarios.

Key Competencies

• Translating requirements into evaluation scenarios that actually catch failures.
• Analytical thinking and structured problem-solving.
• Precision, and a bias toward proving correctness rather than assuming it.
• Ownership, adaptability, and speed of learning.
• Clear communication and cross-functional collaboration.

Learning & Growth Opportunities

• Depth in evaluation design, automation and API-level validation on a production core banking platform.
• Hands-on work with AI-assisted development and evaluation workflows.
• Experience evaluating AI-embedded systems in a regulated domain — a capability few engineers have today.
• Direct collaboration with senior platform engineers, Product and Business Analysis.