Product Engineer

Nxtwave Disruptive Technologies (Hiring for a Client); Pune District; On-site; INR 1,500,000 - 2,800,000; Full time

Job summary

Nxtwave Disruptive Technologies (Hiring for a Client) seeks a Senior Product Engineer to design and ship AI-native features using React.js and Python/Django or FastAPI, with hands-on work on LLM-powered systems in production.

You will own architecture, build reliable AI workflows, and lead reviews while delivering end-to-end products that integrate with external tools and platforms, with a strong emphasis on cost, latency, and scalability.

Qualifications

• 3+ years of experience building and shipping software products.
• Strong proficiency in React.js and Python with Django, or FastAPI with the ability to transition to Django.
• Proven experience building and owning LLM-powered systems in production with real users.
• Hands-on experience with LangGraph or an equivalent LLM orchestration framework.
• Strong understanding of LLM fundamentals, including tokens, context windows, structured outputs, cost, latency, and model limitations.
• Experience with AI agents, tool calling, context engineering, multi-turn state management, and memory handling.
• Understanding of LLM evaluation, regression testing, and production monitoring.
• Knowledge of prompt-injection risks, guardrails, and secure AI application design.
• Experience designing and integrating REST APIs and working with SQL or NoSQL databases.
• Strong system design and architectural decision-making skills.
• Technical leadership experience, including code reviews, mentoring, and improving engineering standards.
• Excellent debugging, problem-solving, communication, and ownership skills.
• Ability to work independently in an ambiguous, fast-paced product environment.

Responsibilities

• Design, develop, and ship end-to-end product features using React.js, Python, and Django.
• Build production-grade LLM applications using frontier models such as Claude and other leading LLMs.
• Develop orchestrated AI workflows using LangGraph, LangChain, or equivalent frameworks.
• Implement AI agents that interact with external tools, APIs, and platforms using MCP and other integration mechanisms.
• Design robust context engineering, retrieval, memory management, and multi-turn conversational workflows.
• Build and maintain evaluation frameworks using golden datasets, regression tests, and quality benchmarks.
• Implement guardrails, prompt-injection protection, structured outputs, and reliable error-handling mechanisms.
• Optimize LLM applications for cost, latency, scalability, and performance.
• Establish observability through tracing, prompt versioning, monitoring, and debugging.
• Make sound architectural decisions, evaluate trade-offs, and choose deterministic solutions wherever appropriate.
• Lead code reviews, mentor engineers, and establish high standards for code quality and system reliability.
• Take ownership of production performance, troubleshoot issues, and continuously improve features based on user feedback.

Skills

React.js

Python

Django

FastAPI

LLM-powered systems

LangGraph

AI workflows

REST APIs design

SQL

NoSQL databases

System design

Technical leadership

Code reviews

Mentoring

Ownership

Education

Bachelor's degree or higher in CS/related

Tools

LangGraph

LangChain

REST APIs

Git

Job description

We are looking for a Senior Product Engineer with strong full-stack development skills and hands-on experience building and deploying AI-powered products using Large Language Models (LLMs). The ideal candidate should be capable of taking features from concept to production, owning system architecture, building reliable AI workflows, and continuously improving product quality.

You will work on AI-native applications involving conversational interfaces, intelligent agents, dynamic user interfaces, and integrations with external tools and platforms.

Key Responsibilities

• Design, develop, and ship end-to-end product features using React.js, Python, and Django.
• Build production-grade LLM applications using frontier models such as Claude and other leading LLMs.
• Develop orchestrated AI workflows using LangGraph, LangChain, or equivalent frameworks.
• Implement AI agents that interact with external tools, APIs, and platforms using MCP and other integration mechanisms.
• Design robust context engineering, retrieval, memory management, and multi-turn conversational workflows.
• Build and maintain evaluation frameworks using golden datasets, regression tests, and quality benchmarks.
• Implement guardrails, prompt-injection protection, structured outputs, and reliable error-handling mechanisms.
• Optimize LLM applications for cost, latency, scalability, and performance.
• Establish observability through tracing, prompt versioning, monitoring, and debugging.
• Make sound architectural decisions, evaluate trade-offs, and choose deterministic solutions wherever appropriate.
• Lead code reviews, mentor engineers, and establish high standards for code quality and system reliability.
• Take ownership of production performance, troubleshoot issues, and continuously improve features based on user feedback.

Mandatory Skills & Qualifications

• 3+years of experience building and shipping software products.
• Strong proficiency in React.js and Python with Django, or FastAPI with the ability to transition to Django.
• Proven experience building and owning LLM-powered systems in production with real users.
• Hands-on experience with LangGraph or an equivalent LLM orchestration framework.
• Strong understanding of LLM fundamentals, including tokens, context windows, structured outputs, cost, latency, and model limitations.
• Experience with AI agents, tool calling, context engineering, multi-turn state management, and memory handling.
• Understanding of LLM evaluation, regression testing, and production monitoring.
• Knowledge of prompt-injection risks, guardrails, and secure AI application design.
• Experience designing and integrating REST APIs and working with SQL or NoSQL databases.
• Strong system design and architectural decision-making skills.
• Technical leadership experience, including code reviews, mentoring, and improving engineering standards.
• Excellent debugging, problem-solving, communication, and ownership skills.
• Ability to work independently in an ambiguous, fast-paced product environment.