AI Engineer

We are seeking an experienced AI Engineer-Python with expertise in building intelligent systems using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) architecture, and agentic frameworks such as LangChain, LangGraph, or AutoGen. The ideal candidate will be responsible for designing, developing, and deploying scalable AI solutions using Python and cutting-edge AI technologies.

Key Responsibilities:

Design and implement AI solutions using LLMs for real-world applications.

Develop and optimize RAG architectures to integrate LLMs with vector databases for contextual retrieval.

Build and manage intelligent agents using LangChain, LangGraph, or AutoGen.

Fine-tune and prompt engineer LLMs for task-specific outcomes.

Work closely with data scientists, backend engineers, and product teams to deliver end-to-end AI features.

Design scalable architectures for real-time and batch processing pipelines.

Evaluate and integrate new tools/libraries to improve system performance and capabilities.

Document code, pipelines, and design decisions clearly and effectively.

Required Skills:

Programming: Strong in Python

AI/LLM: Hands-on experience with OpenAI, Hugging Face, or similar LLM APIs/frameworks

Prompt Engineering: Proven ability to design optimized prompts for various use cases

RAG Architecture: Deep understanding and experience implementing Retrieval-Augmented Generation pipelines

Vector Databases: Experience with FAISS, Pinecone, Weaviate, ChromaDB, or similar tools

Agentic Libraries: Experience building agent-based workflows using LangChain, LangGraph, AutoGen, or similar tools