CodeNicely
Website:
codenicely.in
Job details:
CodeNicely
We at CodeNicely are looking for an experienced Django Backend Engineer (3+ years) who combines deep backend expertise with a forward-thinking approach to AI/ML integration. You will be engaged in all phases of the software development lifecycle — from architecting robust backend systems and designing scalable APIs to building intelligent, AI-powered services that drive our products. You will participate in design meetings, consult with clients to refine, test, and debug systems, and collaborate with third-party partners to achieve business and technology goals. You will work closely with Frontend Developers, Mobile Engineers, Product Managers, and AI/ML teams to deliver high-quality, scalable, and intelligent backend solutions.
Key Responsibilities:
- Design, develop, and maintain scalable backend systems and RESTful/GraphQL APIs using Django and Django REST Framework (DRF).
- Architect and build AI/ML integration layers — connecting backend services to LLM APIs (OpenAI, Claude, Gemini, etc.), embedding models, and cloud-hosted inference endpoints.
- Design and implement Retrieval-Augmented Generation (RAG) pipelines — including document ingestion, chunking strategies, vector embedding generation, and semantic search using vector databases (Pinecone, Weaviate, pgvector, Qdrant, or ChromaDB).
- Build and manage prompt engineering workflows on the backend — including prompt templating, chaining, output parsing, guardrails, and fallback logic for LLM-powered features.
- Implement AI-powered backend features such as intelligent search, content generation, automated summarization, classification, and recommendation engines.
- Design efficient database schemas, perform data modeling, write optimized queries, and manage migrations using Django ORM and PostgreSQL/MySQL.
- Build and maintain data pipelines that feed AI/ML models — including data cleaning, preprocessing, feature extraction, and storage.
- Implement robust authentication, authorization, and security practices (OAuth2, JWT, role-based access control).
- Design and implement background task processing and async workflows using Celery, Redis, or Django Channels — critical for handling long-running AI inference tasks.
- Integrate third-party services, payment gateways, cloud storage, and external APIs alongside AI/ML service endpoints.
- Write comprehensive unit tests, integration tests, and API tests to ensure reliability — including testing non-deterministic AI outputs with threshold-based and fuzzy-match assertions.
- Optimize application performance through caching (Redis, Memcached), query optimization, database indexing, and efficient AI response caching strategies.
- Set up and maintain CI/CD pipelines for automated testing, linting, and deployment.
- Use AI-assisted development tools (GitHub Copilot, Claude, Cursor, etc.) to accelerate code generation, debugging, code review, and documentation.
- Write clean, maintainable, well-documented code with clear documentation of AI integration patterns, model versioning, and API contracts.
- Create and maintain comprehensive documentation — system architecture, database schemas, API specifications, AI/ML integration guides, and deployment runbooks.
- Stay updated with the latest in Django ecosystem, Python backend best practices, and emerging AI/LLM technologies relevant to backend development.
Basic Qualifications:
- Minimum 3 years of hands-on backend development experience with Django and Python.
- Strong CS fundamentals in object-oriented design, design patterns, data structures, and algorithms.
- Proficiency in Python (must-have) with clean, Pythonic coding practices.
- Solid experience with Django REST Framework for building and maintaining APIs.
- Strong working knowledge of relational databases (PostgreSQL preferred) — schema design, query optimization, and migrations.
- Understanding of RESTful API design principles and best practices.
- Familiarity with version control using Git (GitHub, GitLab, Bitbucket).
- Foundational understanding of AI/ML concepts — how LLMs work, when to use different model types, and how to integrate AI services into backend architectures.
- Experience or strong willingness to work with AI-assisted coding tools for development productivity.
Good to Have Qualifications:
- Hands-on experience integrating LLM APIs (OpenAI, Claude, Gemini) into production backend systems — including prompt management, streaming responses, token optimization, and error handling.
- Experience building RAG systems — document processing pipelines, vector embeddings, semantic search, and vector database management (Pinecone, pgvector, Weaviate, ChromaDB).
- Familiarity with LLM orchestration frameworks like LangChain, LlamaIndex, or Haystack.
- Experience with AI agent frameworks and function-calling patterns for building autonomous backend workflows.
- Knowledge of prompt engineering best practices — prompt templating, few-shot learning, output parsing, and safety guardrails.
- Experience with GraphQL (Graphene-Django or Strawberry).
- Hands-on experience with asynchronous task queues (Celery, Redis, RabbitMQ) and Django Channels.
- Familiarity with containerization and orchestration (Docker, Kubernetes).
- Experience with cloud platforms (AWS, GCP, or Azure) — including AI/ML-specific services like AWS Bedrock, Google Vertex AI, or Azure OpenAI Service.
- Knowledge of caching strategies (Redis, Memcached) and CDN integration.
- Experience with microservices architecture and event-driven systems.
- Understanding of DevOps practices — CI/CD, infrastructure as code, monitoring, and logging (ELK, Prometheus, Grafana).
- Knowledge of non-relational databases (MongoDB, DynamoDB).
- Familiarity with WebSockets and real-time communication — especially for streaming LLM responses.
- OWASP security awareness and experience with secure coding practices.
- Good communication skills and ability to translate complex technical and AI concepts for non-technical stakeholders.
- Ability to work in a dynamic, fast-paced environment.
- Hands-on experience with Linux operating systems and server administration.
Perks:
- World-class office infrastructure.
- No formal dress code.
- Friendly and exciting work culture.
- Exposure to AI-first product development — build real products powered by LLMs, RAG pipelines, and intelligent automation.
- Direct interaction with national and international clients to build innovative, AI-powered digital products.
- We'd love to hear from you! 👉 Apply now by sending your portfolio and resume to careers@codenicely.in
Click on Apply to know more.