AI Application Development Build and maintain AI-powered applications using LLM APIs (OpenAI, Claude, Gemini, etc.) Implement prompt engineering strategies and optimize model interactions for performance and cost Develop custom AI workflows including retrieval-augmented generation (RAG) systems Create robust error handling, fallback mechanisms, and response validation systems Model Implementation & Fine-tuning Fine-tune open-source models (Llama, Mistral, etc.) for specific use cases and domains Implement training pipelines using modern frameworks (PyTorch, Hugging Face Transformers) Conduct model evaluation, A/B testing, and performance optimization Manage model versioning and experiment tracking Production Deployment & Operations Deploy AI models and applications using FastAPI, Docker, and Kubernetes Build scalable microservices architecture for AI applications Implement monitoring, logging, and alerting for production AI systems Optimize inference performance, latency, and resource utilization Integration & Data Engineering Integrate AI capabilities into existing systems and workflows Build data pipelines for model training and inference Work with vector databases and embedding systems Implement caching strategies and data preprocessing pipelines Required Qualifications Experience 3+ years of experience in machine learning or software engineering 1+ years of hands-on experience with generative AI and LLM integration Demonstrated experience deploying ML models in production environments Technical Skills Proficiency with LLM APIs and SDKs (OpenAI, Anthropic, Google, etc.) Experience fine-tuning transformer models using Hugging Face, PyTorch, or similar Strong proficiency in Python and modern software development practices Hands-on experience with FastAPI, Docker, and containerization Experience with Kubernetes for container orchestration Knowledge of RESTful API design and microservices architecture Core Competencies Understanding of transformer architectures, embeddings, and attention mechanisms Experience with prompt engineering and model optimization techniques Familiarity with MLOps practices and tools (model versioning, monitoring, CI/CD) Strong debugging and troubleshooting skills Ability to work with large-scale data and distributed systems Preferred Qualifications Experience with vector databases (Pinecone, Weaviate, Chroma, etc.) Knowledge of retrieval-augmented generation (RAG) implementation Experience with model quantization and optimization techniques Familiarity with cloud platforms (AWS, GCP, Azure) and their AI services Experience with streaming and real-time AI applications Knowledge of AI safety and responsible AI practices Experience with specific domains (NLP, computer vision, etc.)