Python Architect – Generative AI

Company Overview

Company information is not specified.

Job Summary

We are looking for a hands-on Python Architect with a strong foundation in backend engineering and recent production experience in Generative AI. The ideal candidate will have 10 years of core Python development experience, along with 2–2.5 years of focused engineering work in Generative AI and microservices. This role is perfect for individuals passionate about architecting scalable AI solutions, writing production-grade code, and enabling DevOps practices for AI-powered microservices in enterprise environments.

Responsibilities

• Architect and implement Python-based microservices integrating Generative AI capabilities.
• Design GenAI-powered solutions using Retrieval-Augmented Generation (RAG) pipelines and LLM orchestration engines.
• Develop RESTful APIs and backend services using FastAPI or Flask integrated with OpenAI or Azure OpenAI, or open-source models.
• Work with DevOps engineers to enable CI/CD, monitoring, and observability for Generative AI pipelines.
• Collaborate with ML engineers and data scientists to optimize Generative AI system performance and scalability.
• Lead design sessions, code reviews, and mentor junior engineers on architectural best practices.
• Implement agentic workflows using Semantic Kernel, LangGraph, or similar orchestration tools.
• Ensure system reliability, scalability, and security across GenAI-enabled services.

Qualifications

• Expert-level Python development skills, including experience with FastAPI, Flask, and asyncio.
• Strong understanding of microservices architecture and distributed systems.
• Hands-on experience with Generative AI tools: LangChain, LlamaIndex, Hugging Face Transformers.
• Practical knowledge of deploying LLMs on cloud platforms (Azure OpenAI preferred).
• Experience with REST API design and integration with external AI services.
• Familiarity with vector databases like FAISS, Pinecone, or Weaviate.
• Proficiency in DevOps practices: CI/CD with GitHub Actions, Docker, Kubernetes, Terraform.
• Proven ability to design scalable, maintainable, and testable AI-driven applications.

Preferred Skills

• Experience with agentic orchestration systems such as Autogen, Semantic Kernel, or LangGraph.
• Exposure to fine-tuning open-source LLMs and deployment in containerized environments.
• Understanding of AI observability, performance tuning, and system logging.
• Background in MLOps and collaboration with Data Science/ML teams.
• Familiarity with agile development and cross-functional engineering collaboration.

Experience

10–12 Years of experience in software development with a focus on backend engineering and Generative AI.

Environment

The role is based in Noida, Bangalore, Hyderabad, and Pune.

Salary

Estimated salary budget is ₹2,00,000.

Growth Opportunities

Potential career advancement opportunities within the company are not specified.

Benefits

Details on offered benefits are not specified.