Senior Python Engineer | LLM & Generative AI Architect

Job Title: Senior Python Engineer | LLM & Generative AI Architect

Experience: 6+ Years (Mandatory)

Location: Ahmedabad, India

Work Mode: On-site

Shift Timing: 2:00 PM 11:00 PM IST

Employment Type: Full-time

Core Focus: Production LLMs, Generative AI, RAG Systems, Fine-tuning, ML Pipelines

Role Overview

We are hiring a Senior Python Engineer LLM & Generative AI Architect to lead the design, development, and deployment of production-grade Generative AI solutions .

This role is strictly for engineers who have moved beyond PoCs and prototypes and have real experience building scalable, reliable LLM systems such as RAG pipelines, fine-tuned models, and AI-powered APIs .

You will play a key role in transforming business problems into high-performance, cost-optimized AI systems running in real-world environments.

Key Responsibilities

• Design, implement, and optimize LLM-based and Generative AI solutions for production use
• Architect and lead Retrieval-Augmented Generation (RAG) systems for context-aware applications
• Perform LLM fine-tuning, calibration, and prompt optimization to improve accuracy, latency, and cost efficiency
• Build and manage end-to-end ML pipelines , including data ingestion, embeddings generation, and vector indexing
• Work with vector databases to enable fast and reliable semantic search
• Integrate deployed AI models into existing platforms through scalable and secure APIs
• Collaborate with engineering and product teams to ensure smooth production rollout and maintenance

Required Technical Skills & Experience

• 6+ years of production-level Python development
• Strong hands-on experience with Large Language Models (LLMs) and Generative AI systems
• Proficiency in PyTorch or TensorFlow for model training and inference
• Practical experience with Hugging Face Transformers ecosystem
• Hands-on expertise with LangChain or LlamaIndex for LLM orchestration
• Experience working with Vector Databases such as Pinecone, Weaviate, or Milvus
• Solid understanding of embeddings, semantic search, and RAG pipelines
• Working knowledge of MLOps , including model deployment, monitoring, and lifecycle management in cloud environments