Python/Generative AI Specialist - LLM Applications

Risk Resources seeks a Python/Generative AI Specialist to design and deploy production-grade LLM applications for financial-institution and enterprise clients. The role focuses on information processing and decision-making workflows, including applications for risk assessment and internal knowledge management. The specialist will work with data engineering teams and senior stakeholders to turn business requirements into scalable solutions.

Responsibilities

• Architect Generative AI pipelines in Python for data retrieval and synthesis.
• Develop and optimize retrieval-augmented generation (RAG) frameworks that produce accurate, context-aware responses from large proprietary datasets.
• Design prompt-engineering strategies to improve model performance and reliability across business use cases.
• Use LangChain and related orchestration frameworks to build modular AI agents that automate workflows.
• Refine outputs with stakeholders to meet regulatory standards and business objectives; monitor and fine-tune production LLMs for low latency and response quality.

Requirements

• 6–10 years of professional experience in software engineering or data science, with a focus on modern AI stacks.
• Expertise in Python for data-intensive applications and AI-driven services; proven production experience implementing and scaling LLM solutions using LangChain and RAG.
• Advanced prompt-engineering skills, analytical ability, and the ability to explain technical concepts to non-technical stakeholders and clients.
• A degree in Computer Science, Engineering, or a related quantitative field, with a foundation in algorithms and system design.

This is a full-time, hybrid role across the Mumbai, Bangalore, Hyderabad, Chennai, or Pune offices.