AI native Engineer

LTM; Chennai District; Hybrid; INR 1,500,000 - 2,700,000; Full time

Job summary

LTM invites an AI Native Engineer in Chennai with 4–12 years of software experience to design AI-driven development pipelines and configuration frameworks that keep AI tools productive across the SDLC.

You will work with Java, .NET, JavaScript, or Python, utilize Copilot or Claude Code in production, and implement validation scripts while mentoring teams on safe, scalable AI-augmented practices.

Qualifications

• 4+ years of software engineering experience.
• Proven expertise in at least one core stack (Java, .NET, JS, Python).
• Experience using AI assistants in production projects and shipping features.

Responsibilities

• Design configuration frameworks and validation pipelines for AI-enabled development.
• Ship features and fix bugs using AI coding assistants with measurable velocity gains.
• Balance AI autonomy with human oversight through effective prompting and token management.
• Mentor teams on AI-augmented practices and safe automation strategies.

Skills

Java

.NET

JavaScript

Python

Tools

GitHub Copilot

Claude Code

Cursor

Windsurf

Codex

Job description

AI Native Engineer

We're seeking engineers with 4-12 years of experience who leverage AI coding assistants to ship quality software faster. You'll design configuration frameworks and validation pipelines that make AI tools reliably productive across the SDLC, from requirements to deployment.

You Will Excel If You:

• Demonstrate deep expertise in at least one core stack (Java, .NET, JavaScript, or Python) with hands-on experience using AI assistants in production projectsshipping features, fixing bugs, and refactoring with measurable velocity gains
• Have proficiency in GitHub Copilot or Claude Code (required); experience with multiple assistants like Cursor, Windsurf, or Codex is a strong advantage
• Design context management strategies and automated workflows (validation scripts, guardrails, pre/post-execution checks) that encode project conventions and enforce quality gates
• Balance AI autonomy with human oversight—optimizing for iteration speed through effective prompting, token management, and knowing when to delegate vs. review
• Debug AI workflows by analyzing assistant configurations, conversation history, and capability restrictions
• Mentor teams on AI-augmented practices: effective prompting patterns, reusable templates, and safe automation strategies