Senior Generative AI

Job Title: Senior Generative AI

Experience: 5+ Years

Role Overview

We are looking for a highly skilled Senior Generative AI & Backend Engineer to design, build, and scale AI-powered backend systems. The ideal candidate will have strong hands-on experience with Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), and modern Python backend frameworks, along with the ability to deploy production-grade, secure, and scalable AI solutions.

Key Responsibilities

Generative AI Development

• Develop, integrate, and optimize generative AI solutions using frameworks such as LangChain, Llama-Index, or similar tools.
  
• Apply advanced prompt engineering techniques to design effective prompts and ensure high-quality LLM responses across diverse use cases.
  
• Optimize LLM performance through prompt tuning, hyperparameter adjustments, response caching, and evaluation strategies.
  
• Design and implement Retrieval-Augmented Generation (RAG) pipelines using vector databases such as Pinecone, Weaviate, Supabase, or PGVector.
  
• Work with embeddings and similarity search techniques to build personalized and context-aware AI solutions.
  
• Develop and support multimodal AI workflows, including text, image, and video understanding or generation.
  
• Integrate observability and monitoring tools to track LLM performance, quality, latency, and reliability in production environments.
  

Backend Engineering

• Design, develop, and maintain scalable backend services using Python frameworks such as FastAPI, Django, or Flask.
  
• Build and maintain RESTful APIs for seamless integration between AI services and external systems.
  
• Optimize and manage relational databases (PostgreSQL, MySQL) alongside vector databases for AI-driven workflows.
  
• Implement asynchronous programming patterns to support high-concurrency and low-latency systems.
  
• Integrate third-party SDKs, APIs, and services while ensuring reliability and fault tolerance.
  
• Develop backend pipelines to handle multimodal data processing, including text, images, and video.
  
• Manage background jobs and scheduled tasks using Celery, cron jobs, or equivalent queueing systems.
  
• Use Docker and containerization best practices for reproducible and scalable deployments.
  
• Ensure backend systems are secure, scalable, and production-ready, following industry best practices.
  

Required Qualifications (Essential)

• 58 years of experience in backend development, with strong proficiency in Python.
  
• Hands-on experience with FastAPI, Django, or Flask.
  
• Solid understanding of Generative AI, including LLMs, embeddings, prompt engineering, and RAG architectures.
  
• Experience working with vector databases such as Pinecone, Weaviate, Supabase, or PGVector.
  
• Strong knowledge of relational databases (PostgreSQL, MySQL).
  
• Experience deploying AI solutions to production environments using Docker.
  
• Proficiency in asynchronous programming, background task processing, and concurrent systems.
  
• Strong testing and debugging skills, including unit and integration testing (e.g., Pytest).
  
• Ability to troubleshoot performance bottlenecks and optimize system reliability.
  

Preferred Qualifications

• Experience with cloud platforms such as AWS, GCP, or Azure (VMs, containers, or serverless services).
  
• Basic understanding of frontend technologies (HTML, CSS, JavaScript; React or Angular is a plus).
  
• Experience with observability, logging, and monitoring tools for backend and LLM systems.
  
• Familiarity with multimodal AI, agentic workflows, and emerging generative AI trends.
  
• Knowledge of secure coding practices, API security, and backend system hardening.
  
• Relevant certifications in AI, machine learning, or cloud technologies are a plus.