Python With AI Developer

We are looking for an expert-level Python developer with deep expertise in Large Language Models (LLMs) and AI/ML frameworks. The ideal candidate will be skilled in building high-performance applications, fine-tuning AI models, and leveraging modern Python (3.9+) features including async/await for concurrent API integrations. Experience with AWS Bedrock and vector database technologies is essential, with MLOps capabilities considered a strong plus.

Key Responsibilities

• Design, develop, and deploy Python-based applications using Python 3.9+ features such as async/await for concurrent API calls.
  
• Fine-tune and optimize AI models using PyTorch and TensorFlow.
  
• Build and integrate applications using LLM libraries and frameworks like FastAPI and LangChain.
  
• Implement RAG (Retrieval-Augmented Generation) pipelines and manage vector embeddings for efficient knowledge retrieval.
  
• Work with DynamoDB and vector database solutions for AI-driven search and data processing.
  
• Develop and manage prompt engineering for LLM-based solutions.
  
• Integrate and utilize AWS Bedrock for deploying and managing LLM applications.
  
• Collaborate using GIT workflows and contribute to CI/CD pipelines for continuous delivery.
  

Required Skills

• Python (must-have): Expert-level coding, concurrency (async/await), API integration.
  
• AI/ML (must-have): LLM's, RAG implementation, vector embeddings.
  
• Frameworks: FastAPI, LangChain.
  
• Model Development: PyTorch, TensorFlow fine-tuning.
  
• Databases: DynamoDB, vector databases.
  
• Cloud Services: Understanding of AWS Bedrock.
  
• Version Control & DevOps: GIT, CI/CD pipeline knowledge.
  

Good to Have

• MLOps experience for ML lifecycle automation and deployment.
  
• Prior experience with large-scale production AI systems.
  

Qualifications

• Bachelors or Master’s degree in Computer Science, AI/ML, or related field.
  
• 5+ years of professional experience in Python development and AI/ML systems.
  
• Proven track record of deploying LLM-based applications.