Job Description

Key Responsibilities:
Design and implement GenAI-powered content summarization workflows using AWS services.
Utilize Amazon Bedrock, SageMaker, or custom LLMs on EC2/EKS for building and deploying summarization models.
Build and manage embedding pipelines using models like Amazon Titan Embeddings, OpenAI, or Hugging Face models.
Integrate and optimize vector databases (e.g., Pinecone, Amazon OpenSearch, Weaviate, FAISS, or Milvus) for efficient semantic retrieval.
Develop APIs and interfaces to access summarization outputs in real time.
Ensure system scalability, performance, and security following AWS best practices.
Collaborate with business and product stakeholders to understand use cases and refine output formats.
Stay updated with the latest in GenAI, prompt engineering, and retrieval-augmented generation (RAG) techniques.
__________________________________________________________
Required Skills:
3-6+ years of experience in AI/ML, NLP, or data science.
Proven experience with AWS AI/ML services: Amazon Bedrock, SageMaker, Lambda, Step Functions, S3, API Gateway, IAM, etc.
Hands-on experience with LLMs (OpenAI, Anthropic, Cohere, etc.) and content summarization techniques.
Proficiency in Python, especially for AI workflows and AWS SDK (boto3).
Deep understanding of vector databases and semantic search.
Experience with RAG (Retrieval-Augmented Generation) architectures.
Familiarity with prompt engineering and LLM tuning strategies.
Strong problem-solving, communication, and stakeholder management skills.

Job Types: Full-time, Permanent

Benefits:

Flexible schedule Health insurance Life insurance Paid sick time Paid time off Provident Fund Work from home
Expected Start Date: 27/08/2025