Job Summary:
We are seeking a highly skilled Python Developer with a minimum of 5 years of development experience and hands-on experience building AI-based applications. The ideal candidate should have strong expertise in AI application development, Retrieval-Augmented Generation (RAG) workflows, and embedding models. Prior experience working with Large Language Models (LLMs) such as Llama or Granite is essential, along with proficiency in pre- and post-processing of RAG workflows.
This is a 100% onsite opportunity as the developer will be required to collaborate closely with key application developers and architects, ensuring seamless integration and deployment of AI-powered applications within enterprise environments.
Key Responsibilities:
-
Develop AI-powered applications leveraging LlamaIndex or LangChain.
-
Implement RAG (Retrieval-Augmented Generation) workflows, including pre- and post-processing techniques.
-
Work with embedding models to optimize document retrieval and ranking.
-
Build and optimize APIs using FAST API.
-
Develop prompt engineering techniques for both text and images to optimize LLM outputs.
-
Deploy and manage containerized applications using Docker, OpenShift, or Kubernetes.
-
Work with vector databases on Azure for AI-driven search and retrieval.
-
Integrate and manage OIDC-based authentication for secure application access.
-
Optimize application performance, scalability, and security in cloud environments.
-
Understand Kafka and event-driven programming for real-time data processing.
-
Collaborate with key application developers and architects to align AI development with enterprise system requirements.
Requirements:
-
3-5 years of development experience in Python and software engineering.
-
Hands-on experience building AI-based applications using modern frameworks.
-
Prior experience working with LLMs such as Llama or Granite.
-
Hands-on experience with LlamaIndex or LangChain for AI-driven workflows.
-
Deep understanding of RAG (Retrieval-Augmented Generation) workflows, including pre- and post-processing techniques.
-
Proficiency in embedding models for search and ranking.
-
Strong prompt engineering experience for text and images.
-
Experience in FAST API for building high-performance APIs.
-
Good understanding of Docker, OpenShift, or Kubernetes for container orchestration.
-
Familiarity with vector databases on Azure (e.g., Azure Cosmos DB, FAISS, Chroma).
-
Experience with OIDC authentication frameworks and security best practices.
-
Understanding of Kafka and event-driven programming.
-
Working knowledge of NoSQL databases and MS SQL.
-
Basic understanding of Kotlin and React to collaborate effectively with frontend and mobile teams.
-
Strong problem-solving skills and ability to work in a collaborative, onsite environment.
Nice to Have (Red Hat-Based Products & AI Model Serving):
-
Experience with Red Hat OpenShift Service Mesh.
-
Knowledge of Red Hat Quay for container registry management.
-
Experience with model serving using OpenShift AI and vLLM.
-
Knowledge of pipeline automation using KubeFlow Pipelines and Elyra.Role & responsibilities
