Description

You will architect and drive the technical design of scalable, production-grade AI/ML systems.

This role is on-site.

Responsibilities

• Design end-to-end Retrieval-Augmented Generation (RAG) pipelines, including retriever configuration, semantic search optimization, and extractor logic.
• Define and implement LLM-based agentic workflows, managing tool integration, memory handling, and multi-agent decision making.
• Lead the architectural design of enterprise applications, spanning data ingestion, fine-tuning, prompt engineering, and output evaluation.
• Conduct performance benchmarking and cost optimization, making critical system design trade-offs for GenAI solutions.
• Translate complex business needs into robust, AI-powered system designs through collaboration with product and ML teams.

Required Skills

• 5+ years of experience designing complex AI/ML or GenAI architectures at scale.
• Deep knowledge of Retrieval-Augmented Generation (RAG), including end-to-end retriever-reader pipeline design.
• Proficiency with Python and core AI libraries like LangChain, Transformers, and LlamaIndex.
• Solid experience with LLM agent frameworks, including LangChain, Semantic Kernel, and Haystack.
• Strong grasp of vector databases, including ANN algorithms, and the ability to justify their use over traditional RDBMS.
• Experience with embedding models (OpenAI, Cohere, HuggingFace) and trade-offs between vector stores and semantic indexing.
• Deep understanding of agentic concepts: Tools, Memory (episodic, long-term, vector-based), and Dynamic Planning.
• Experience working with commercial and open-source LLMs (e.g., GPT-4, Mistral, LLaMA).

Preferred Skills

• Experience with fine-tuning LLMs or deploying proprietary models.
• Understanding of MLOps and deployment strategies for LLM pipelines.

Key Skills

Education

Any Gradute