Description

You will design and build scalable, production-grade backend systems for AI/ML applications, focusing on search, recommendations, and RAG pipelines.

This role is on-site.

Responsibilities

• Build and scale AI-powered backend systems, including search, recommendations, and RAG-based assistants.
• Design end-to-end RAG pipelines covering ingestion, embeddings, retrieval, and ranking.
• Implement robust APIs and distributed services with idempotency, concurrency control, retries, and circuit breakers.
• Manage streaming and batch data pipelines, feature stores, and offline evaluation jobs.
• Deploy services using Kubernetes and implement observability via OpenTelemetry, Prometheus, and Grafana.

Required Skills

• 5+ years of backend engineering experience with Python or Java.
• Hands-on experience building AI/ML products, specifically RAG, search, or recommendation systems.
• Deep understanding of RAG pipelines, including chunking, embeddings, indexing, and vector similarity.
• Strong distributed systems design skills, including API design and fault tolerance mechanisms.
• Experience with vector databases (FAISS, Milvus, Pinecone, Elasticsearch).
• Proficiency in Kubernetes and cloud infrastructure for deployment and management.
• Ability to define and track retrieval quality metrics such as Precision, Recall, nDCG, and MRR.
• Experience with ML platform components like feature stores and experimentation frameworks.

Preferred Skills

• Experience with agentic AI systems, tool/function calling, and model serving architectures.
• Strong understanding of data privacy and security controls in production environments.

Key Skills

Education

Any Graduate