Python Developer

Python Engineer with AI Development Capabilities

Location: Noida

Experience: 4–6 Years

Job Summary We are seeking an experienced

Python Engineer with AI Development Capabilities for

Noida with

4–6 years of experience in backend and web application development. The ideal candidate should possess strong expertise in

Python, Django, Flask, FastAPI, REST API development, and modern Generative AI technologies . The role requires hands-on experience in building AI-powered applications using

LangGraph, LangChain, LLMs, and vector databases , while developing scalable, secure, and production-ready backend systems.

About Us CodeVyasa is a mid-sized product engineering company that works with top-tier product and solutions organizations such as

McKinsey, Walmart, Razorpay, Swiggy , and others. We are a team of

550+ engineers , driving innovation across Product & Data Engineering, with a strong focus on:

• Agentic AI
• Robotic Process Automation (RPA)
• Full Stack Engineering
• Generative AI (GenAI) Solutions

Primary Skills (Mandatory)

• Python
• Django / Flask / FastAPI
• RESTful API Development
• LangGraph
• LangChain
• Generative AI (GenAI)
• Large Language Models (GPT-4, Claude, Llama, etc.)
• Retrieval Augmented Generation (RAG)
• Vector Databases (Pinecone, PGVector, ChromaDB, Weaviate)
• PostgreSQL / MySQL
• Git & Version Control

Roles & Responsibilities Web Application Development

• Design, develop, and maintain scalable RESTful APIs using Django, Flask, and FastAPI.
• Build secure, modular, and high-performance web applications and backend services.
• Implement authentication and authorization mechanisms using OAuth2, JWT, and session-based approaches.
• Collaborate with frontend teams to ensure seamless API integration and end-to-end application functionality.
• Follow software development best practices, code reviews, testing, and deployment processes.
• Participate in CI/CD workflows using GitHub, GitLab, Docker, Jenkins, or similar tools. AI & GenAI Development
• Design and develop intelligent AI-powered applications using LangGraph and LangChain frameworks.
• Integrate OpenAI, Anthropic Claude, Hugging Face, Llama, and other LLMs into enterprise applications.
• Build and optimize Retrieval Augmented Generation (RAG) systems for knowledge retrieval and contextual responses.
• Develop AI agents, workflow orchestration systems, and multi-step reasoning pipelines.
• Work with vector databases such as Pinecone, PGVector, ChromaDB, or Weaviate for semantic search and retrieval.
• Optimize prompt engineering, model interactions, and inference workflows for production use cases.
• Collaborate with product and engineering teams to translate business requirements into AI-driven solutions. Database & Backend Engineering
• Design and maintain database schemas and backend architectures.
• Develop efficient SQL queries and optimize database performance for large-scale applications.
• Ensure application scalability, security, monitoring, and reliability.
• Integrate third-party APIs, services, and cloud-native solutions.

Secondary Skills (Preferred)

• AWS, Azure, or GCP Cloud Platforms
• Docker & Kubernetes
• CI/CD Pipelines
• Agentic AI Frameworks
• Prompt Engineering
• Hugging Face Ecosystem
• Redis / Celery
• Microservices Architecture
• Monitoring & Observability Tools
• MLOps Concepts and Deployment Pipelines

Required Qualifications

• Bachelor's degree in Computer Science, Information Technology, Engineering, or a related field.
• 4–6 years of professional experience in Python application development.
• Strong hands-on experience with Django, Flask, or FastAPI.
• Proven experience developing and consuming RESTful APIs.
• Hands-on experience building GenAI applications using LangGraph and LangChain.
• Experience working with Large Language Models such as GPT-4, Claude, Llama, or equivalent models.
• Strong understanding of RAG architectures and vector databases.
• Proficiency in PostgreSQL, MySQL, and backend system design.
• Solid understanding of software engineering principles, design patterns, and code modularity.
• Experience with Git-based development workflows and collaborative engineering practices.

Good to Have

• Experience building AI Agents and Agentic AI workflows.
• Knowledge of fine-tuning, evaluation, and monitoring of LLM-based systems.
• Experience with cloud-native deployments on AWS, Azure, or GCP.
• Exposure to MLOps practices and model deployment frameworks.
• Familiarity with event-driven and microservices architectures.
• Open-source contributions or personal AI/ML projects.

Why Join CodeVyasa?

• Work on cutting-edge AI and GenAI-driven product engineering initiatives.
• Exposure to Agentic AI, LLMs, RAG architectures, and enterprise-scale applications.
• Collaborate with highly skilled engineers on impactful global projects.
• Continuous learning and career growth opportunities.
• Flexible and employee-friendly work culture.
• Competitive compensation and comprehensive benefits package.
• Free healthcare coverage for employees and dependents.