AI Product Engineer

PingAura AI; Mumbai; Remote; INR 900,000 - 1,300,000; Full time

Job summary

PingAura AI is hiring an AI Product Engineer to own features end to end—where value comes from AI behavior, not CRUD. You will talk to customers, shape the product, write code, and ship it into production daily.

This remote-first startup, backed by CXO angels and major cloud providers, moves fast and ships to real paying customers from day one. You will collaborate across UI, APIs, data models, and agent behavior.

Qualifications

• 2+ years building and shipping production web applications (frontend + backend).
• Experience using AI tools daily and opinions on their use.
• Familiarity with server-rendered frameworks, REST APIs, and relational databases.
• Strong TypeScript skills with async patterns and type safety.

Responsibilities

• Own AI-powered features end to end from schema to UI.
• Ship production code with testing and monitoring multiple times a day.
• Collaborate with customers to translate pain points into product changes.
• Design data models and write performant queries in PostgreSQL.
• Build server-side logic: API routes, workers, and integrations.
• Develop prompts, tool use, evals, and fallbacks for LLMs.
• Review AI-generated code and ensure production readiness.

Tools

TypeScript

Next.js

PostgreSQL

React Server Components

OpenAI / LLMs

Langfuse

Sentry

Redis

pg_cron

pgmq

Turborepo

pnpm

AWS / GCP

Cursor

Claude Code

Job description

About The Role

AI is changing how people find things. When someone asks AI answer surfaces like ChatGPT, Gemini, or Claude a question, some brands show up and others don't. PingAura helps brands show up - and monetize that presence. Our flagship product is the AI Coworker, a real agent that does the work of an AEO team for our customers.

About The Role

AI is changing how people find things. When someone asks AI answer surfaces like ChatGPT, Gemini, or Claude a question, some brands show up and others don't. PingAura helps brands show up - and monetize that presence. Our flagship product is the AI Coworker, a real agent that does the work of an AEO team for our customers.

We are hiring an AI Product Engineer to own features end to end - where most of the value comes from how the AI behaves, not from CRUD. You will talk to customers, shape the product, write the code, and ship it.

We are a small founding team backed by 14 CXO angel investors, Google for Startups, and AWS, with paying enterprise customers and a product running in production every day.

This is not a prompt-only role. It is for an engineer who can ship product across UI, APIs, data models, agent behavior, evals, and production reliability.

Responsibilities

• Own AI-powered features end to end - database schema through API through agent behavior through UI
• Ship product where the hard part is making the LLM do the right thing: prompts, tool use, evals, fallbacks
• Build and extend the AI Coworker, dashboards, audits, and visibility tools
• Design data models and write performant queries against Postgres
• Build server-side logic: API routes, background jobs, agent runners, third-party integrations
• Write evals before you ship. Measure what good looks like, then prove it
• Ship production code multiple times a day with proper testing and monitoring
• Join customer calls and translate pain points into product improvements

You may be a good fit if

• You have 2+ years building and shipping production web applications across frontend and backend
• You build with AI tools every day - Cursor, Claude Code, Codex, or comparable - and have opinions about how to use them well
• You are comfortable reviewing AI-generated code instead of blindly accepting it
• You are comfortable with server-rendered frameworks, REST APIs, relational databases, and deployment workflows
• You have worked with Postgres (or similar) and can write non-trivial queries, migrations, and schema designs
• You write solid TypeScript - async patterns, error handling, type safety
• You have built at least one feature where the core logic was a large language model call, and you know why "it works in the demo" is not the same as "it works in production"
• You are interested in LLM evals, observability, and production reliability
• Ship rather than plan - small things today over big things next month
• You communicate clearly in a small, remote-first team

Strong candidates may also have

• Production experience with Next.js Server Actions, React Server Components, or comparable server-rendered patterns
• Experience integrating LLM APIs with tool calling, structured outputs, and streaming
• Experience with OpenAI, Anthropic, Gemini, or other LLM providers in production
• Familiarity with observability or eval tools such as Langfuse, Sentry, Braintrust, RAGAS, DeepEval, or comparable tooling
• Working knowledge of Python for eval scripts, automation, or AI tooling
• Exposure to GCP or AWS in production
• Background in search, content, or marketing technology

What we work with

• Language: TypeScript across the stack
• Web: Next.js 16 (App Router), React 19, Server Actions, Tailwind, Shadcn UI
• Database: PostgreSQL on Supabase with row-level security; pg_cron and pgmq for scheduled and queued work
• Cache and rate limiting: Redis on Memorystore - caching, distributed rate limiting, queue patterns
• AI: OpenAI, Gemini, and Anthropic via a multi-provider routing layer
• Observability: Langfuse for LLM traces, Sentry for errors, plus standard cloud logging and monitoring
• Cloud: GCP for compute, data, and storage; AWS for CDN
• Workflow: Turborepo monorepo, pnpm, Cursor and Claude Code daily

Compensation

• Competitive salary benchmarked for early-stage startups in India

Why this team

The problem is brand new and the team is small. You ship to real paying customers from day one, you work directly with the founders, and the decisions move fast.