Technical lead-Backend Engineering

Myntra Engineering
The Myntra Engineering team develops the technology platform that drives our customers' shopping experience and ensures the efficient movement of products from suppliers to their final destinations. Our work spans a variety of areas, including building massive-scale web applications, creating engaging user interfaces, developing big-data analytics, mobile apps, workflow systems, and inventory management solutions.
As a lean technology team, every individual's contribution is significant. You will have the chance to be part of a rapidly expanding organization and gain comprehensive exposure to all components of a complete e-commerce platform.
About the Team - Ad Tech Platform
The Ad Tech Platform team at Myntra builds the engine that powers millions of shopping experiences daily and helps thousands of sellers to give visibility to their products and help in generating revenue. We are a high-impact, fast-paced group of engineers sitting at the intersection of massive-scale distributed systems and advanced machine learning. As we evolve our infrastructure, we are moving beyond traditional ad-serving to pioneer the next generation of product discovery, heavily investing in semantic search and vector databases to enhance ad relevance. Our culture is defined by deep technical ownership, high-scale engineering excellence, and a collaborative spirit that bridges the gap between production software and data science. Joining us means solving some of the most complex challenges in e-commerce at scale, working with a team that values innovation, reliability, and technical craft.
Key Responsibilities
Design & Architecture: Lead the end-to-end design, architecture, and implementation of complex, high-scale distributed ad-serving systems. Ensure high availability, low latency, and reliability using Java, Kafka, Redis, and Aerospike.
ML Pipelines & Online Serving: Design, code, troubleshoot, and support scalable ML pipelines and online model-serving systems for the ad platform — from data ingestion and feature engineering through training to real-time, low-latency inference within the ad-serving path.
ML Integration & Strategy: Bridge the gap between Data Science and Engineering. Own the productionization of ad ranking and response-prediction models (CTR/CVR), ensuring experimental models from the DS team are seamlessly integrated, scalable, and performant in production. Work hand-in-hand with data scientists to optimize model performance and the underlying ML infrastructure.
Search Innovation: Spearhead the migration and optimization of our search infrastructure. Lead the implementation and fine-tuning of semantic search capabilities and vector databases to significantly improve ad relevance.
Technical Leadership: Set engineering benchmarks and code standards. Mentor team members, conduct rigorous architectural reviews, and foster a culture of technical craft and innovation within the team.
Cross-Functional Collaboration: Partner closely with Product, Data Platform and Data Science stakeholders to translate business objectives into scalable technical roadmaps. Manage the lifecycle of ad-tech features from conception to deployment, ensuring that system performance aligns with business KPIs.
Desired Skills
Backend & Distributed Systems Mastery
Must have: Deep expertise in Java (Spring Boot), Kafka, Solr, Redis, and Aerospike.
Expert-level skills in System Design and High-scale reliability engineering.
Applied AI/ML Engineering
Solid knowledge of machine learning model architectures and inference, with proven experience productionizing ranking/prediction models and managing the collaborative model lifecycle.
Experience building large-scale ML infrastructure for online recommendation, ads ranking, personalization, or search.
Proven experience with semantic search and vector databases.
Hands-on experience with ML frameworks such as PyTorch or TensorFlow; exposure to modern serving and optimization stacks (e.g., vLLM, TensorRT, JAX) is a strong plus.
Experience with model serving and optimization for real-time, latency-critical inference applications.
Good to Have
Knowledge of LLM fundamentals — transformer architecture, training/inference lifecycles, and optimization techniques — and interest in applying generative AI to advertising use cases.
Experience with big data and streaming frameworks (e.g., Apache Spark, Kafka) for processing large-scale ad-event data.
Familiarity with containerization and orchestration (Docker, Kubernetes) for deploying ML services at scale.
Understanding of the advertising/monetisation domain — sponsored products, ad auctions, budget pacing, or response prediction (CTR/CVR).
Experience
A minimum of 6.5 years of experience, featuring a strong, demonstrable history of building and maintaining high-scale distributed backend systems, with recent experience or strong project-based knowledge in production-grade ML/DS model deployment and online serving.
Education
B. Tech/M. Tech in computer science engineering, Mathematics, or related fields from a premier institute.