AI Engineer

We are looking for an AI Engineer / GenAI Engineer with strong hands-on experience in Agentic AI, LLM-based applications, Python, AWS AI/ML services, and data engineering. The candidate should be capable of designing, developing, integrating, and deploying AI-powered solutions in a production environment.

• Design and develop Agentic AI solutions, AI agents, multi-step workflows, and tool/function calling.
• Build LLM-based applications using OpenAI, Anthropic, AWS Bedrock, or similar platforms.
• Develop RAG, knowledge-based AI solutions, prompt engineering, embeddings, and vector search.
• Work extensively with AWS AI/ML services, particularly:
  • AWS Bedrock
  • Amazon Textract / OCR
  • Amazon SageMaker
  • Amazon Comprehend and other relevant AI services
• Develop AI/ML backend services and integrations using Python and frameworks such as FastAPI/Flask.
• Design and maintain ETL/data pipelines for AI and business applications.
• Work with databases including DynamoDB, PostgreSQL, and other relational/NoSQL databases.
• Integrate structured and unstructured data into AI pipelines and knowledge systems.
• Build and maintain REST APIs and microservices supporting AI solutions.
• Implement CI/CD pipelines using Git/Bitbucket, Docker, and cloud deployment practices.
• Work with AWS services such as Lambda, S3, SQS, SNS, ECS/EKS, API Gateway, CloudWatch, and other supporting services.
• Implement monitoring, logging, security, scalability, and performance optimization for AI applications.
• Collaborate with engineering and business teams to convert use cases into scalable AI solutions.
  
  

• Strong hands-on Python development experience.
• Practical experience with Generative AI and LLMs.
• Strong understanding and hands-on experience with Agentic AI / AI Agent development.
• Experience with AWS Bedrock and other AWS AI/ML services.
• Experience with OCR / document processing, preferably Amazon Textract.
• Experience building RAG and LLM-powered applications.
• Good knowledge of DynamoDB and PostgreSQL.
• Experience with ETL/data pipelines and data processing.
• Experience with Git/Bitbucket and CI/CD pipelines.
• Good understanding of REST APIs, microservices, Docker, and cloud-based application deployment.
• Strong problem-solving and software engineering skills.
  
  

• Experience with LangChain, LangGraph, LlamaIndex, CrewAI, or similar frameworks.
• Experience with vector databases such as pgvector, Pinecone, OpenSearch, Qdrant, or similar.
• Experience with AWS Lambda, S3, SQS, Step Functions, ECS/EKS, API Gateway, and CloudWatch.
• Exposure to Machine Learning / ML model integration.
• Experience with AI evaluation, observability, security, and cost optimization