Key skills
AWSAzureCloudDockerFlaskGoogle Cloud PlatformKubernetesNumpyPandasPythonPyTorchScikit-LearnTensorflowAIMachine LearningMLGenAILLMRAGLangChainAgenticTensorFlowscikit-learnNumPyHugging FaceMLOpsLangGraphPineconeFastAPIGCPGoogle CloudRESTfulGitCI/CDCommunication
About this role
Role Overview
- Design, develop, and deploy LLM-powered applications using RAG architectures
- Build AI agents and multi-agent systems using LangChain and LangGraph
- Develop scalable Python-based ML/AI solutions using PyTorch, TensorFlow, Hugging Face, Scikit-learn, Pandas, and NumPy
- Implement vector search and semantic retrieval solutions using FAISS, Pinecone, or similar technologies
- Fine-tune, evaluate, and optimize LLMs through prompt engineering and advanced evaluation techniques
- Develop RESTful APIs using FastAPI or Flask
- Deploy and scale AI solutions on AWS, Azure, or GCP
- Implement MLOps/LLMOps best practices, CI/CD pipelines, monitoring, and governance controls
Requirements
- 5+ years of Python development and Machine Learning experience
- 2+ years of hands-on experience with GenAI, RAG, and LLM applications
- Strong expertise in LangChain and/or LangGraph
- Experience with vector databases, semantic search, and retrieval systems
- Knowledge of Agentic AI, prompt engineering, and workflow orchestration
- Experience with Docker, Kubernetes, Git, and cloud deployment platforms
- Strong problem-solving and communication skills
Tech Stack
- AWS
- Azure
- Cloud
- Docker
- Flask
- Google Cloud Platform
- Kubernetes
- Numpy
- Pandas
- Python
- PyTorch
- Scikit-Learn
- Tensorflow