Job Summary:

We are seeking an experienced Senior Python Engineer – Generative AI to design, develop, and deploy large-scale AI-driven applications. The ideal candidate will bring strong expertise in Python development, LLM integration, and knowledge-augmented architectures (RAG/KAG), along with hands-on experience in building robust APIs, AI workflows, and scalable agentic systems. This role requires a solid understanding of modern data processing pipelines, distributed systems, caching strategies, and containerized deployments.

Key Responsibilities:

• Develop and maintain large-scale Python applications leveraging Generative AI technologies.
• Integrate and utilize pre-trained LLMs via APIs (OpenAI, Anthropic, Hugging Face, etc.).
• Design and implement Retrieval-Augmented Generation (RAG) and Knowledge-Augmented Generation (KAG) pipelines.
• Build document processing and text extraction workflows for search, indexing, retrieval, and document intelligence.
• Develop robust REST APIs using FastAPI or Flask.
• Create and orchestrate workflows with n8n.
• Integrate and build agentic AI systems using Langchain, vLLM, Langraph, Agno, and (optionally) Foundry agents.
• Develop and optimize complex agentic pipelines for decision-making and automation.
• Implement distributed task queues using Celery and RabbitMQ.
• Design and implement various caching mechanisms: semantic caching, in-memory caching (Redis, Memcached), distributed caching (Redis Cluster), etc.
• Work with RDBMS, NoSQL, and Vector Databases (Pinecone, Qdrant, Milvus, Chroma DB, Elasticsearch).
• Containerize applications using Docker for scalable deployment.
• Ensure code quality and reliability through unit testing (PyTest).
• Monitor application health and performance using Prometheus and Grafana.
• Leverage Microsoft Azure services such as Durable Functions, Service Bus, and Document Intelligence for cloud-native solutions.
• Collaborate with cross-functional teams to define requirements and deliver solutions.
• Maintain comprehensive documentation and adhere to best coding practices.

Required Skills & Qualifications

• 5+ years of professional Python development experience.
• Experience integrating LLMs and NLP APIs (OpenAI, Anthropic, Hugging Face, etc.).
• Practical expertise in RAG/KAG architectures for knowledge retrieval/augmentation.
• Experience with document processing, NLP workflows, and document intelligence solutions.
• Advanced API development skills with FastAPI and/or Flask.
• Hands-on experience with agentic/graph-based frameworks: Langchain, vLLM, Langraph, Agno.
• Experience with workflow automation tools (n8n).
• Proficiency with distributed task queues (Celery, RabbitMQ).
• Expertise in caching mechanisms: semantic caching, in-memory (Redis/Memcached), distributed caching schemes.
• Experience with RDBMS, NoSQL, and Vector Databases (Pinecone, Qdrant, Milvus, Chroma DB, Elasticsearch).
• Skilled in containerization using Docker.
• Practical experience with monitoring tools: Prometheus and Grafana.
• Proficient in writing unit tests using PyTest.
• Familiarity with Azure services: Durable Functions, Service Bus, Document Intelligence.
• Strong communication and teamwork abilities.
• Commitment to code quality, documentation, and software engineering best practices.

Preferred/Plus Skills

• Experience working with Foundry agents or similar agentic frameworks.
• Experience implementing YOLO models for vision or document AI applications.
• Familiarity with Google AI Studio for rapid prototyping or LLM integration.
• Prior experience deploying or orchestrating GenAI solutions on Microsoft Azure.

Equal Opportunity Statement

• We value diversity and inclusion. As an equal opportunity employer, we welcome applicants from all backgrounds and walks of life.

Security & Confidentiality Statement

• This role may involve access to sensitive business information. The selected candidate is expected to follow internal information security policies and maintain strict confidentiality when handling proprietary or confidential data.