About the Role
We are seeking an experienced AI Engineer with expertise in Python, SQL, and GenAI frameworks, including LLM architecture, RAGs, embeddings, prompt tuning, and agentic AI. This role involves building and deploying advanced AI solutions.
Responsibilities
- Apply agentic AI patterns to develop intelligent systems.
- Build and deploy AI agents for various applications.
- Develop and deploy production APIs to support AI services.
- Containerize AI workloads using technologies like Docker.
- Deploy machine learning models on leading cloud platforms such as AWS, Azure, and GCP.
- Develop robust RAG (Retrieval Augmented Generation) pipelines.
- Implement advanced LLM (Large Language Model) architectures.
- Integrate data from diverse sources via REST APIs.
- Tune prompts for LLMs to optimize performance and accuracy.
- Utilize embeddings and vector databases for efficient data representation and retrieval.
Requirements
- Proficiency in Python and SQL.
- Strong understanding and experience with GenAI frameworks.
- Expertise in LLM architecture, RAGs, embeddings, and prompt tuning.
- Experience with agentic AI concepts and implementation.
- Familiarity with cloud platforms (AWS, Azure, GCP) for model deployment.
- Knowledge of containerization tools like Docker.
- Experience with building and integrating REST APIs.
- Skills in using vector databases.
- Education: Bachelor of Engineering, Bachelor of Science, Master of Engineering, or Master of Science.
Technical Skills
- AWS
- Asynchronous programming
- Autogen
- Azure
- CrewAI
- Docker
- Embeddings
- FastAPI
- GCP
- Google APIs
- Guardrails
- LLM Architecture
- Langchain
- Langgraph
- MLOps
- Node.js
- Prompt Tuning
- Python
- RAG
- REST APIs
- React
- SQL
- Server-Sent Events
- Tool-Calling
- TypeScript
- Vector Databases
- WebSockets