Generative AI / Agentic AI Engineer (AWS)

About The Role

We are looking for a skilled Generative AI / Agentic AI Engineer with strong expertise in AWS cloud services to design, develop, and deploy production-grade AI applications. The ideal candidate should have hands-on experience building LLM-powered applications, AI agents, RAG pipelines, and scalable cloud-native solutions on AWS.

Key Responsibilities

• Design and develop Generative AI and Agentic AI applications using Large Language Models (LLMs).
• Build AI agents capable of reasoning, planning, tool usage, and workflow automation.
• Develop Retrieval-Augmented Generation (RAG) pipelines using vector databases.
• Integrate LLMs through APIs such as OpenAI, Anthropic Claude, Amazon Bedrock, or open-source models.
• Deploy scalable AI applications using AWS cloud services.
• Build REST APIs and backend services for AI-powered applications.
• Design prompt engineering strategies and optimize model performance.
• Monitor, evaluate, and improve AI model quality, latency, and cost.
• Collaborate with Product, Data Science, and Engineering teams to deliver AI solutions.
• Ensure security, scalability, and best practices for cloud-native AI applications.

Mandatory Skills

• 3+ years of software development experience.
• Hands-on experience with Generative AI and Agentic AI development.
• Strong knowledge of LLMs (GPT, Claude, Llama, Mistral, etc.).
• Experience with RAG (Retrieval-Augmented Generation).
• Experience with AI orchestration frameworks such as:
• LangChain
• LangGraph
• LlamaIndex
• CrewAI
• AutoGen (preferred)
• Strong programming skills in Python.
• Hands-on experience with AWS services including:
• Amazon Bedrock
• Lambda
• API Gateway
• ECS/EKS
• EC2
• S3
• IAM
• CloudWatch
• DynamoDB or RDS
• Experience with Docker and containerized deployments.
• Experience integrating REST APIs and third-party services.
• Familiarity with Git and CI/CD pipelines.

Preferred Skills

• Experience with MCP (Model Context Protocol).
• Experience building multi-agent systems.
• Knowledge of vector databases such as Pinecone, Weaviate, Milvus, FAISS, or OpenSearch.
• Experience with embedding models and semantic search.
• Experience deploying open-source LLMs.
• Knowledge of Kubernetes.
• Experience with Terraform or AWS CloudFormation.
• Familiarity with MLOps and LLMOps practices.
• Experience with monitoring tools such as LangSmith, Phoenix, or MLflow.

Qualifications

• Bachelor's or Master's degree in Computer Science, Information Technology, Artificial Intelligence, or a related field.
• AWS Certification (Associate or Professional) is a plus.

Mandatory Screening Criteria Mandatory (Experience)

• Must have 3+ years of software development experience.
• Must have 1+ year of hands-on experience building production Generative AI or Agentic AI applications.

Mandatory (Technical Skills)

• Strong Python programming.
• Hands-on experience with LLMs.
• Experience with RAG.
• Experience with LangChain, LangGraph, LlamaIndex, CrewAI, or AutoGen.
• Strong AWS experience, preferably with Amazon Bedrock.
• Experience deploying applications on AWS.

Preferred

• MCP (Model Context Protocol)
• Multi-Agent AI systems
• Vector Databases
• Prompt Engineering
• LLM Evaluation
• Kubernetes
• Docker
• CI/CD
• Terraform
• MLOps/LLMOps

Skills: bedrock,agentic ai,aws,gen ai,amazon,cloud,models