Job Title

Job Title:Senior Python Engineer | LLM & Generative AI Architect Experience:6+ Years (Required) Location:Ahmedabad, India (On-site) Focus:Production Gen AI, RAG, Fine-tuning, ML PipelinesArchitect the Next Generation of Intelligent Applications We are searching for a visionarySenior Python Engineer(6+ years) to drive our Generative AI initiatives. If you are past the prototype stage and ready tobuild, deploy, and scaleproduction-ready LLM solutions—from crafting sophisticated RAG systems to fine-tuning models for specific business needs—we want you on our AI engineering team. This role is for someone ready to leverage deep Python expertise to solve real-world problems with cutting-edge AI.Core Impact Areas (What You Will Do):As a key member of the AI team, you will be responsible for end-to-end delivery of intelligent systems: LLM Implementation:Design, implement, and optimize solutions using Large Language Models (LLMs) and Generative AI frameworks. RAG Architecture:Lead the design and implementation of Retrieval-Augmented Generation (RAG) systems for high-accuracy, context-aware applications. Model Optimization:Engage in model fine-tuning and calibration to maximize performance and minimize latency/cost in production environments. Data Pipelines:Architect and manage robust ML pipelines for data ingestion, embeddings generation, and vector database management. Integration & APIs:Integrate deployed models into existing enterprise systems via resilient and scalable APIs.️ Required Technical Expertise:We are looking for deep, hands-on experience in the following areas: Python Mastery:6+ years of production-level Python development. AI/ML Frameworks:Strong command ofPyTorchorTensorFlow , and hands-on experience with theHugging Face Transformersecosystem. LLM Tools:Proven expertise using orchestration frameworks likeLangChainorLlamaIndex . Data Architecture:Working experience withVector Databases(e.g., Pinecone, Weaviate, Milvus) and embedding techniques. MLOps Understanding:Familiarity with deploying, monitoring, and maintaining models in a cloud environment.