ML Engineer - Search

Zepto · Bengaluru

  • Experience4–7 yrs
  • SalaryNot disclosed
  • Work modeonsite
  • Levelmid
  • Posted2 Sept 2026
Apply for this job

About Zepto

Zepto is hiring in Bengaluru in ecommerce retail. This role looks for around 4+ years of experience.

Skills

  • Natural Language Processing
  • Recommender Systems
  • Machine Learning
  • Classification
  • Regression
  • Clustering
  • Anomaly Detection
  • Pattern Recognition
  • Deep Learning
  • Large Language Models
  • Retrieval-Augmented Generation
  • Agentic AI
  • Product Search
  • Personalization
  • Lexical Search
  • Semantic Search
  • Learning-to-Rank Algorithms
  • Recommendation System Design
  • Transformer Architecture
  • BERT
  • Information Retrieval
  • Generative Modeling
  • Next-Purchase Prediction
  • Sequential Recommendation
  • Session-Based Recommendation
  • Python
  • PyTorch
  • TensorFlow
  • NLTK
  • Vector Search
  • Approximate Nearest Neighbor Search
  • Knowledge Graphs
  • Agentic Workflows
  • Context Management
  • Memory Management
  • Real-Time Personalization
  • Context Window Optimization
  • Retrieval-Augmented Context Injection
  • State Management
  • Bachelor's Degree
  • Master's Degree
  • Computer Science
  • Statistics
  • Mathematics

The role

An AI and machine learning engineer at an e-commerce marketplace builds product search and personalization systems using natural language processing, recommender systems, and generative AI. The role develops semantic search, learning-to-rank algorithms, and agentic workflows for tailored product discovery.

Full job description

Requirements:

Strong experience in NLP, Recommender Systems, and Machine Learning algorithms (classification, regression, clustering, anomaly detection, pattern recognition techniques, deep learning, LLMs/RAG/Agentic AI).

Hands-on experience building ML systems for Search & Personalisation use cases (AI-powered product search based on lexical search, semantic search, learning-to-rank algorithms, and recommendation systems).

Deeper understanding of Transformer architecture, BERT and other embedding models for information retrieval techniques.

Advancements in Large Language Models and Generative Modelling.

Experience building deep learning models for next-purchase and next-basket recommendation (e. g., sequential/session-based recommenders based on next-purchase prediction) to personalise what and when customers are likely to buy next.

Key Technical Skills:

Languages & Frameworks: Python; PyTorch/TensorFlow; NLTK, transformer-based embedding models (BERT and similar).

Search & Retrieval: Lexical and semantic search, vector/ANN search, learning-to-rank algorithms and recommendation system design.

ML Techniques: Classification, regression, clustering, anomaly detection, pattern recognition, deep learning, knowledge graphs, and LLMs/RAG/Agentic AI.

Experience designing and building agentic workflows (multi-step reasoning, planning, tool-use, and orchestration) for product search and personalisation use cases.

Hands-on experience with memory handling and context management at scale, including short-term/session memory and long-term user memory to support coherent, personalised agentic experiences across sessions.

Experience integrating personalisation signals (user preferences, purchase history, intent) into agentic product search pipelines, enabling agents to retrieve, re-rank, and respond with results tailored to the individual user.

Familiarity with techniques for managing large-scale context (context window optimisation, retrieval-augmented context injection, state/session management) across multi-turn, multi-agent interactions in production systems.

Preferred Skills:

Experience designing and deploying ML solutions at large scale (billions of records).

Experience leveraging parallel processing techniques (multithreading, multiprocessing, distributed computing) to build high-performance, scalable machine learning pipelines and optimise large-scale data processing workloads.

Exposure to OpenSearch, ElasticSearch or Solr will be an added advantage.

Familiarity with real-time data streaming technologies such as Kafka, Flink, etc.

Understanding of the fundamentals of data governance, fairness, and ethical AI principles.

Required Qualifications:

Bachelor's or Master's degree in Computer Science, Statistics, Mathematics, or equivalent practical experience.

3-6 years of relevant experience building large-scale ML systems.