Gen AI & Data Engineer

Before You Apply

We kindly request that you do not apply if your experience with Generative AI is limited to basic API integrations in a notebook environment. Applications will not be considered if they do not demonstrate a proactive approach to challenges like IP blocking and dynamic content in web scraping, or if unfamiliarity with advanced concepts such as RAG, token economics, MCP, or vector databases is present. Candidates who require explicit task definition from a Product Manager, rather than taking independent ownership, should also refrain from applying.

About Quickeee

Quickeee is a dynamic, fast-growing startup headquartered in Mumbai, India. We are at the forefront of transforming the fast fashion sector, providing customers with rapid 60-minute delivery and a personalized AI-driven styling service. Our vision is to create a best-in-class, technology-centric platform that prioritizes speed, individuality, and superior design.

To support our advanced AI concierge and proprietary catalog systems, we are seeking a talented Gen AI & Data Engineer to develop and scale our foundational AI infrastructure.

Role Overview

We are looking for a Gen AI & Data Engineer with 2-3 years of backend development experience, including a minimum of 1 year of hands-on, production-grade Generative AI expertise. In this role, you will be responsible for our AI features and data pipelines, collaborating directly with the technical founder to build our Luxury Concierge and integrate it using FastAPI into our existing NestJS ecosystem.

Key Responsibilities

AI Systems & Agentic Workflows

• Develop and deploy agent-based workflows utilizing frameworks like LangChain and LangGraph.
• Engineer a context-aware AI concierge designed for highly personalized shopping experiences.

Data & Scraping Infrastructure

• Construct robust scraping pipelines employing tools such as Playwright or Scrapy.
• Implement processes for the extraction, cleaning, and structuring of large-scale catalog data.

RAG & Vector Systems

• Build and manage RAG (Retrieval-Augmented Generation) pipelines linked to live inventory data.
• Work with and optimize vector databases, including options like Pinecone or Milvus.

Optimization & Performance

• Focus on optimizing prompts, reducing latency, and managing token usage effectively.
• Implement caching strategies and efficient model routing mechanisms.

Image & Data Processing

• Develop pipelines for image preprocessing, leveraging libraries like OpenCV.
• Prepare data for multimodal models that combine vision and text inputs.

Backend Integration

• Create microservices using the FastAPI framework.
• Ensure seamless integration of AI systems with our core backend architecture.

Qualifications

• 2-3 years of professional experience in Python backend development.
• A minimum of 1 year of practical experience working with Large Language Models (LLMs) in production environments.
• Proficiency in FastAPI and best practices for API design.
• Demonstrated experience with frameworks such as LangChain, LlamaIndex, or equivalent.
• Familiarity with cloud AI APIs like OpenAI and Gemini.
• Proven experience working with vector databases.
• A strong understanding of web scraping techniques and data extraction methodologies.
• Solid grasp of system design principles and scalability considerations.

What We Seek in a Candidate

• A strong builder mentality with a high degree of ownership and accountability.
• The ability to work autonomously and deliver results efficiently.
• A clear comprehension of the trade-offs between cost, latency, and quality in AI solutions.
• A practical, problem-solving approach to real-world challenges.
• Comfort and adaptability in a fast-paced startup culture.

Benefits and Perks

• Competitive salary coupled with startup equity options.
• Direct influence and ownership over core AI systems and their architecture.
• Opportunity to work on impactful, real-world Gen AI applications, beyond experimental prototypes.
• A high-impact role with a flat hierarchy and rapid execution cycles.
• Flexible working hours to promote work-life balance.
• Close collaboration with the founding team and core technology personnel.

Why Embark on a Career with Quickeee

• Contribute to innovations at the intersection of AI, e-commerce, and design.
• Tackle significant real-world problems at a large scale.
• Thrive in an environment that emphasizes high ownership and accelerated professional growth.
• Play a pivotal role in shaping our core technology from its inception.