Phyton Developer (GenAI & Banking)

Job Responsibilities: 

• Develop object-oriented applications using Python with expert-level software engineering practices.
• Work with Vector Databases for embedding storage and retrieval optimization.
• Design and implement GenAI lifecycle management and RAG pipelines (chunking, embedding, retrieval, re-ranking, summarization) for banking use cases.
• Evaluate and test embedding models and frameworks for performance, latency, memory, and cost optimization.
• Apply prompt engineering , hallucination mitigation, and grounding techniques for AI solutions.
• Build API-driven applications using FastAPI , API Gateway , and integrate with MongoDB , Redis, and front-end frameworks ( Angular/React ).
• Develop utilities, automation frameworks , and data pipelines to support AI/ML and GenAI initiatives.
• Create monitoring dashboards and automation scripts for system health and performance.
• Collaborate with DevOps teams using enterprise tools (Git/Bitbucket , Jenkins , SonarQube , Artifactory , Ansible ).
• Work with large cross-functional teams to deliver secure, compliant, and scalable solutions.

 Experience:

• 5+ years of experience in object-oriented programming using Python with strong software development skills.
• Deep experience in GenAI lifecycle management and RAG pipelines.
• Expertise in prompt engineering and AI safety techniques.
• Hands-on experience with MongoDB, Redis, Fast API, containerization (Docker/Kubernetes), and API integrations.
• Strong knowledge of model testing and evaluation frameworks for performance and reliability.
• Solid understanding of DevOps practices and enterprise tooling.
• Understanding of Kafka queue integration and configurations.
• Ability to deploy python code on to containers using OpenShift and docker etc.
• Ability to work effectively with large cross-functional teams in a regulated environment.

Preferred Skills: 

• Experience with cloud platforms (AWS, Azure) and serverless architectures.
• Knowledge of Agentic architectures and orchestration frameworks.
• Exposure to AI/ML use cases in regulatory relations or risk analytics.
• Explore Agentic architectures for orchestration and multi-step reasoning in AI workflows.