Description

Architect and implement scalable AI Agents, Agentic Workflows, and GenAI applications for complex business needs.

This role is on-site.

Responsibilities

• Develop, fine-tune, and optimize lightweight LLMs, evaluating models like Claude, Azure OpenAI, and open-source alternatives.
• Design and deploy Retrieval-Augmented Generation (RAG) and Graph RAG systems using vector databases and knowledge bases.
• Curate enterprise data using connectors integrated with AWS Bedrock's Knowledge Base/Elastic, leveraging MCP and A2A communication.
• Build and maintain Jupyter-based notebooks on platforms like SageMaker and MLFlow/Kubeflow running on Kubernetes (EKS).
• Establish and enforce validation procedures, bias mitigation, and safety protocols for production-ready GenAI deployment.

Required Skills

• 3+ years experience in applied GenAI or LLM-based solutions with a BA or MS in AI/Data Science.
• Deep expertise in prompt engineering, fine-tuning, RAG, GraphRAG, and vector databases (e.g., AWS KnowledgeBase / Elastic).
• Proven experience with cloud-native AI development using AWS SageMaker, Bedrock, and MLFlow on EKS.
• Strong programming skills in Python and ML libraries (Transformers, LangChain).
• Deep understanding of Gen AI system patterns, architectural best practices, and Evaluation Frameworks.
• Experience designing ingestion pipelines to extract, chunk, enrich, and anonymize data from PDFs, video, and audio.
• Proficiency with scalable frameworks (Apache Spark, PySpark) for multimodal pipelines and ETL/ELT.
• Experience integrating GenAI solutions with enterprise platforms via API-based methods.

Preferred Skills

• Experience with Kubernetes (EKS) orchestration for ML workloads.
• Knowledge of CI/CD pipelines for MLOps.

Key Skills

Education

Any Gradute