Product Engineer (Junior)

Venxr; Pune District; On-site; INR 500,000 - 800,000; Full time

Benefits offered by this job

Health cover

Team offsites

Flexible culture

Job summary

VenXR in Pune is seeking a Junior Product Engineer to build with LLMs, taking ownership from idea to production. You’ll ship features end-to-end, with a model in the loop, and contribute to campaigns planning interfaces and tool integrations.

Required: 1–2 years shipping product; strong React.js and Python/Django skills (or FastAPI with Django); experience with at least one LLM-backed feature; REST APIs and databases; hands-on debugging and ambiguity tolerance.

Qualifications

• 1–2 years shipping product.
• Proficient in React.js and Python/Django (or FastAPI) and able to reach Django quickly.
• Experience with at least one LLM-backed feature touching real users.
• REST APIs, SQL/NoSQL, and basic system design for scalable solutions.
• Strong debugging skills and comfort with ambiguity and minimal hand-holding.

Responsibilities

• Build features end to end with a model-in-the-loop.
• Own production features from concept to deployment.

Skills

1-2 years product shipping

React.js

Python/Django

LLM integration

System design

Tools

Django

React.js

LangGraph

LangChain

Docker

SQL/NoSQL

MCP

Job description

Product Engineer (Junior) — VenXR

VenXR builds AdsGPT: brands plan, run and optimise their ad campaigns by talking to it. We're hiring a Product Engineer, one to two years in, who builds with LLMs rather than around them.

What You’ll Build

Features, end to end — from a half-formed idea to production, and you own what happens after it ships. Most of what you build will have a model in the loop: campaign planning that reasons about a brand's goals, interfaces that assemble themselves from whatever the model surfaced, agents calling real tools against real ad platforms.

Tech Stack

Frontend: React.js
Backend: Python, Django
AI: Claude and other frontier models, LangChain / LangGraph, MCP

AI-native, and we mean it literally

Most job ads get this wrong, so plainly: using Claude to write code is not what we mean. Everyone does that. We mean LLMs as the material the product is built from. You'll need working knowledge of:

• Fundamentals — tokens, context windows, cost, latency, structured outputs, why a confident model is often wrong
• Orchestration — LangGraph or equivalent: state, nodes, conditional routing, persistence, interrupts. Not just prompts in a for loop
• Multi-agent patterns — when splitting work across agents helps, and the commoner case where it just multiplies failure modes
• Context engineering — what the model sees at each step: retrieval, compaction, selective injection. Where most of the quality lives
• Memory management — multi-turn state without the window or the bill growing unbounded
• MCP — connecting models to tools and APIs
• Evaluation — knowing whether what you built works, which is harder than building it

What we want is someone who has built at least one real thing with an orchestration framework — past the tutorial, into the part where it broke. Self-taught side projects count; show us.

What You Need

• One to two years shipping product
• React.js, Python with Django — or FastAPI plus the obvious ability to get to Django in a fortnight.
• At least one LLM-backed feature real users touched, where you owned the prompt, the orchestration and the failure modes
• REST APIs, SQL or NoSQL, and enough system design to know when your approach won't survive scale
• Strong debugging, and comfort with ambiguity and almost no hand-holding

Your work speaks louder than your degree. Share links to your GitHub, portfolio, or projects you’ve shipped. That’s what we’ll look at first.

What Helps

Each one moves you up the list.

• Conversational interfaces, and multi-turn state across channels
• LLM evaluation and monitoring — Ragas, LangSmith, Langfuse, or your own harness
• Working knowledge of Generative UI.
• AdTech, MarTech domain knowledge is a plus.
• Cloud infra, Docker, CI/CD
• Explainable or compliance-aware AI in a regulated domain

How We Work

• Customer obsession — curiosity about what your code does to someone's day
• Ownership — chase blockers rather than wait on them
• Stakeholder sense — know when to pull in Product, Design or Business
• High standards — hold your work to a bar nobody is checking
• Disagree and commit — argue the call hard, then back it fully
• Simplify relentlessly — the simplest thing that works beats the cleverest thing that works
• Solidarity — show up for teammates unasked
• Vitality — energy that holds up in month six

In practice: ship fast, test in production more than is strictly comfortable, and sit close enough to the founders that "I'll ask Product" means turning around.

The process

The take-home is the real filter, so here's what it's for.

• Tech screening round — 30 minutes.
• Take-home — a small orchestrated LLM system. Using AI is expected; being unable to defend what it wrote is disqualifying.
• Interview round 1 — we walk through your submission and argue about it.
• Interview round 2 - Technical + Managerial

Baner, Pune. Health cover, team offsites, and a culture that's flexible in the ways that matter rather than the ways that photograph well.

Skills: mcp,django,react.js,langgraph,system design,sql,orchestration,langchain,docker