Skip to content
- Design and develop GenAI solutions leveraging AWS services such as Lambda, Managed Airflow (MWAA), Bedrock, S3, and DynamoDB.
- Build and optimize RAG-based architectures using vector databases and advanced text processing techniques.
- Work with LLMs and enterprise chat platforms including ChatGPT, OpenAI APIs, Anthropic (Claude), and Ollama.
- Develop and maintain enterprise-level MCP servers and GenAI backend services.
- Design and deploy containerized microservices using Docker and Kubernetes.
- Integrate vector databases such as Weaviate for semantic search and knowledge retrieval.
- Ensure scalability, security, observability, and compliance of GenAI solutions in enterprise environments.
- Collaborate with architects, product teams, and stakeholders to align AI solutions with business use cases.
- Provide technical guidance and contribute to architectural decisions for GenAI platforms.
- Strong understanding of AWS services: Lambda, Bedrock, MWAA (Managed Airflow), S3, DynamoDB.
- In-depth knowledge of LLM internals, RAG architectures, vector databases, NLP, and text processing pipelines.
- Hands-on experience with enterprise chat systems using ChatGPT, OpenAI, Anthropic (Claude), and/or Ollama.
- Experience building enterprise-scale MCP servers and AI middleware platforms.
- Proficiency in Docker, Kubernetes, and microservices architecture.
- Hands-on experience with vector databases such as Weaviate (or similar).
- Strong programming experience in TypeScript / JavaScript.
- Experience with API gateways, authentication, and authorization in AI systems.
- Exposure to CI/CD pipelines and MLOps practices for GenAI workloads.
- Knowledge of observability tools for monitoring AI services and model performance.
