Full Stack Engineer

Different Inc.; Bengaluru; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Different Inc. in Bengaluru is building a large, customer-facing part of the product. You will shape design, implementation, and production reliability across the full stack, collaborating with Applied AI engineers on agents and model systems.

This role requires owning features end to end, making hard architectural decisions, mentoring newer engineers, and continuously improving performance, reliability, and user outcomes for marketers relying on the platform.

Qualifications

• 3–6 years building and shipping web products with ownership.
• Expertise in both frontend and backend: TypeScript/React and Node or Python backend.
• Experience shipping at least one LLM-powered feature to real users.
• Strong design decisions and trade-off reasoning with documented outcomes.
• Experience in teams focused on reliability, quality, and scale.

Responsibilities

• Own areas end to end from design to performance in production.
• Make technical decisions and collaborate with AI engineers on agents and models.
• Mentor early-career engineers on hard problems.
• Collaborate with customer-facing teams to decide what to build and evaluate after launch.
• Shape scope with product and design, balance build vs buy vs use existing services.
• Ensure quality through reviews, testing, and design docs.

Skills

Frontend & Backend

TypeScript

React

Node backend

Python backend

Cloud infrastructure

LLM features

Observability

B2B products

Ownership

Tools

Claude Code

Codex

Cursor

Job description

About us

Different is a marketing system that runs demand generation for B2B companies. It handles campaign creation, personalization, and optimization in one place, so lean teams can do more without adding headcount, agencies or point AI solutions. Customers use Different to launch campaigns faster, reach the right buyers, and continuously improve marketing ROI. Between them, Different’s founders have founded two unicorns, led AI at a global marketing software giant, and built platforms used by millions. They bring deep product, technical, and business experience to one shared goal: reimagining how modern marketing works. We are backed by General Catalyst and Lightspeed.

The role

You'll own a large, customer-facing part of the product: how it's designed, how it's built, and how well it holds up once marketers depend on it. You'll make the technical decisions for that area, work with our Applied AI engineers on the agents and model systems behind it, and help earlier-career engineers do their best work. This is not a role for engineers who want to stay specialists in one language or one layer, for example Java-only or Go-only. The work spans the whole stack and changes from week to week.

Product areas:

own one or more areas end to end, from technical design to performance and reliability in production.

Customer problems:

work with customers and customer-facing teams to decide what to build, and check after launch that it worked.

AI features as systems:

build retrieval, tool use and agents where they fit, plus monitoring and fallbacks for when the model gets it wrong.

Evals:

define evals for open-ended problems and scenarios, and use them to decide when a prompt, model or agent change is ready to ship.

Scope and trade-offs:

shape scope with product and design, push back when a simpler version would reach customers sooner, and choose when to build, buy or use an existing service.

Quality and mentoring:

set the bar in your area through code review, testing and design docs, and pair with earlier-career engineers on hard problems.

What we're looking for

• 3–6 years building and shipping web products, with real ownership of systems customers rely on.
• Depth on both frontend and backend, for example TypeScript, React, a Node or Python backend, document or SQL databases, and cloud infrastructure.
• Examples of technical decisions you made, the alternatives you rejected, and how they played out.
• Hands-on experience shipping at least one LLM-powered feature to real users.
• Time on a team known for its bar in experience, quality, reliability or scale, and the practices you brought away from it.
• Curiosity about what's changing in AI: you try new models and tools soon after they come out and have good judgment about which are worth adopting.

Relevant experience may include:

• Working knowledge of Claude Code, Codex or Cursor.
• B2B products, including permissions, multi-tenancy, audit logs or integrations.
• Observability for AI features in production.
• Being an early engineer at a startup.

You don't need any marketing or advertising experience, but you'll need to learn the domain quickly, including how marketers think about audiences and campaigns and what happens after a campaign launches.

Why this is interesting

Most LLM features stop once the model returns an answer. Different keeps going: it decides what to do, acts across channels, sees what happened and adjusts. You'll shape how that loop shows up for marketers, including what they see, approve and come to trust. The hard part is keeping it dependable as models, ad platforms and customer data change underneath it.