Lead AI Engineer

About Info Edge India Ltd.

InfoEdge's mission is to create world-class platforms that transform lives by continuously innovating. Our products and services are built keeping our customers in mind. We always delight our customers by delivering superior value through enhanced offerings on the internet and other platforms. Through our continuous investment across various businesses, especially in cutting-edge technology, machine learning and artificial intelligence (AI), we have built a robust system that constantly increases our predictive powers on customer behaviour, and optimizes and improves our systems. Our various teams tirelessly work together to solve problems, innovate, and create something to empower our customers.

At Info Edge, people are our core competitive advantage and we will continue doing all that is needed to attract and retain the best available talent.

Business: Central Function -Data Science Team.

Title:  Lead AI Engineer 

Required Educational Qualification: BE/ B.Tech/MCA

Experience: 3-7 Years

Work Location: Noida (Sector 132)

• Design and develop a centralized ML platform, including feature store, model registry, experiment tracking, and serving layer.
• Design and own model serving infrastructure, including real-time and batch inference pipelines with SLA-grade reliability.
• Evaluate and implement inference optimization strategies, including quantization, tensor parallelism, vLLM/Triton-based serving, and TensorRT compilation.
• Develop GenAI applications leveraging LLMs, RAG, tool calling, agentic workflows, and knowledge retrieval systems.
• Establish MLOps best practices, including CI/CD for ML, model versioning, drift detection, and automated retraining pipelines.
• Design and maintain automated load-testing pipelines to benchmark model performance under peak and spike traffic conditions.
• Implement advanced deployment strategies such as shadow testing to evaluate new model versions on live traffic without impacting user experience.
• Partner with Data Scientists to productionize models by translating prototype code into scalable, maintainable production services and providing actionable feedback on infrastructure and engineering constraints.
• Collaborate with Platform, DevOps, and Product Engineering teams to embed ML capabilities into the product stack.
• Mentor and lead a team of 3–4 ML Engineers.

• 5–8 years of experience in ML Engineering, MLOps, or AI Platform roles.
• Strong Python programming skills with experience building production-grade applications.
• Hands-on experience building and deploying ML/AI systems in production environments.
• Production experience with LLMs or large-scale deep learning models.
• Experience with serving frameworks such as vLLM, Triton Inference Server, TorchServe, or BentoML.
• Experience with inference optimization techniques including ONNX, TensorRT, quantization (INT8/FP16), 
• Experience with MLflow, Kubeflow, or similar experiment tracking and pipeline orchestration tools.
• Basic understanding of Data Science concepts, including classification, regression, clustering, ranking methods, and evaluation metrics.
• Hands-on experience working with Vector Databases such as Milvus or Chroma.
• Understanding of evaluation frameworks for Generative AI applications, such as DeepEval and Ragas.

• Hands-on experience with feature stores (Feast, Tecton, or custom implementations).
• Experience with data streaming technologies such as Kafka or Kinesis for real-time ML.
• Familiarity with LLM fine-tuning and PEFT techniques (LoRA, QLoRA).
• Experience with LangChain, LangGraph, LlamaIndex, or similar GenAI frameworks.
• Understanding of model safety, fairness, and responsible AI principles.