Role Description
Job Description
Design and implement LLMbased applications using frameworks like LangChain
Develop RAG pipelines integrating vector databases eg FAISS Pinecone Weaviate for knowledge retrieval
Finetune and optimize pretrained LLMs OpenAI Hugging Face etc for domainspecific tasks
Build prompt engineering strategies for effective model interaction
Integrate AI solutions into enterprise systems using Python and APIs
Ensure scalability performance and security of AI applications
Stay updated with the latest advancements in Generative AI and NLP
Required Qualifications
BachelorsMasters in Computer Science AI or related field
Strong experience in Python and AIML frameworks PyTorch TensorFlow
Handson experience with LangChain and RAG architecture
Familiarity with vector databases and embedding models
Knowledge of cloud platforms AWS Azure GCP for AI deployment
Excellent problemsolving and communication skills
Preferred Skills
Experience with OpenAI API Hugging Face Transformers or similar LLM platforms
Understanding of MLOps and model deployment pipelines
Familiarity with data privacy and compliance in AI systems
Skills
Mandatory Skills :
MLOPS,GenAI - LLMOps,Python - Data Science,Machine Learning - AIOPS,Deep Learning - AIOPS