About the role
Date- 25-Jul-26
JD
- Hands-on experience with LLMs (e.g., Amazon Bedrock models, OpenAI-compatible models, open-source LLMs)
- Prompt engineering, prompt chaining, and context optimization
- RAG architecture design (embeddings, vector stores, retrieval strategies)
- Knowledge of fine-tuning vs prompt tuning vs adapters
- Amazon Bedrock (model selection, guardrails, orchestration)
- AWS SageMaker (training, inference, pipelines)
- AWS Lambda, ECS/EKS, Step Functions
- S3, DynamoDB, Aurora / RDS
- IAM, KMS, VPC, CloudWatch for secure AI workloads
- Experience with serverless and container-based AI architectures
- Strong proficiency in Python
- Familiarity with LangChain / LlamaIndex / Semantic Kernel
- REST APIs, FastAPI, Flask
- Experience integrating LLMs with web and enterprise applications
- Embeddings and semantic search
- Vector databases such as OpenSearch, Pinecone, FAISS, Chroma
- Data preprocessing, chunking, and metadata strategies