TechChefz - Python Lead - Generative AI

<p><p><b>Python Lead - Generative AI</b><br/><br/>Experience : 3-6 Years<br/><br/>We are seeking a highly motivated and hands-on Python Lead with a solid background in backend development and practical, production-level experience in Generative AI.<br/><br/> The ideal candidate will have a minimum of 3 years of core Python development experience, with a focus on building and implementing GenAI-powered microservices.<br/><br/> This role is perfect for a senior individual contributor who is passionate about writing clean, scalable code, mentoring junior team members, and driving the implementation of cutting-edge AI Responsibilities : </b></p><p><br/>- Implement and Build : Develop and implement Python-based microservices that integrate Generative AI capabilities.</p><br/>- Design & Contribute : Design and build core components of GenAI-powered solutions, including Retrieval-Augmented Generation (RAG) pipelines and LLM orchestration.<br/><br/>- API Development : Create and maintain robust RESTful APIs and backend services using frameworks like FastAPI or Flask, connecting them with OpenAI, Azure OpenAI, or other open-source models.<br/><br/>- Collaborate on DevOps : Work closely with DevOps and MLOps engineers to ensure the smooth deployment, monitoring, and observability of GenAI pipelines and services.<br/><br/>- Mentor and Guide : Lead design and code review sessions, providing technical guidance and mentorship to junior engineers on best practices and solution implementation.<br/><br/>- Leverage Orchestration : Implement agentic workflows using tools such as Semantic Kernel, LangGraph, or similar orchestration frameworks.<br/><br/>- Ensure Quality : Maintain high standards for system reliability, scalability, and security across all GenAI-enabled Skills Required : </b><br/><br/>- Python : Strong proficiency in Python development, with hands-on experience using frameworks like FastAPI or Flask.<br/><br/>- Microservices : Practical understanding of microservices architecture and distributed systems.<br/><br/>- Generative AI : Experience with core GenAI tools and libraries, including LangChain, LlamaIndex, or Hugging Face Transformers.<br/><br/>- Cloud & APIs : Proven ability to deploy LLMs on cloud platforms (preferably Azure OpenAI) and design and integrate with REST APIs.<br/><br/>- Vector Databases : Familiarity with vector databases such as FAISS, Pinecone, or Weaviate.<br/><br/>- DevOps Fundamentals : Working knowledge of CI/CD practices, Docker, and Kubernetes.<br/><br/>- Problem-Solving : A proven ability to contribute to the design and implementation of maintainable and testable AI-driven / Nice-to-Have Skills : </b></p><br/>- Agentic Systems : Experience with orchestration systems like Autogen, Semantic Kernel, or LangGraph.<br/><br/>- LLM Operations : Exposure to fine-tuning open-source LLMs and their deployment in containerized environments.<br/><br/>- Observability : Understanding of AI observability, performance tuning, and effective system logging.<br/><br/>- Agile Development : Experience working in an agile, cross-functional engineering team</p><br/></p> (ref:hirist.tech)