Description

Key Skills: Machine Learning Engineering, ML Serving, Python, MLOps, Feature Store, Kubernetes, PyTorch, Kafka, Vector Databases, Retrieval, Ranking, LLM, RAG, GenAI

Roles & Responsibilities:

• Lead and build the Machine Learning Engineering function.
• Develop scalable ML platforms for model serving, training, deployment, and monitoring.
• Design low-latency ML inference and feature store solutions.
• Build ML pipelines for training, experimentation, deployment, and production monitoring.
• Develop personalization, retrieval, embedding, and ranking systems.
• Work with vector databases and semantic search technologies.
• Build and deploy LLM, RAG, and GenAI solutions in production.
• Optimize ML infrastructure, GPU usage, performance, and costs.
• Partner with Data Science teams to productionize ML models.
• Define engineering standards, SLOs, monitoring, and incident management practices.
• Hire, mentor, and develop high-performing MLE teams.
• Provide technical leadership and advise senior stakeholders on ML platform decisions.

Experience Required:

• 16-20 years of experience in Software/ML Engineering.
• Strong experience in production ML systems and MLOps.
• Hands-on experience with ML serving, feature stores, and ML platforms.
• Experience with Python and Java/Go/C++.
• Strong knowledge of Kubernetes, Kafka, cloud infrastructure, and distributed systems.
• Experience with retrieval, vector databases, ranking, and recommendation systems.
• Experience with LLMs, RAG, GenAI, and AI infrastructure.
• Strong technical leadership and team-building experience.

Good to Have:

• Experience with Triton, KServe, Ray Serve, Feast, MLflow, Kubeflow, vLLM, or TensorRT-LLM.
• Experience with Qdrant, Vespa, Milvus, Databricks, Spark, or similar technologies.
• Experience in consumer internet or e-commerce platforms.

Education: B.Tech / M.Tech (Dual), B.E., B.Tech in Computer Science, Engineering, or a related field

Key Skills

Education

Any Graduate