Application Support Engineer

Overview

Design, develop, and optimize generative AI solutions using Python and large language models (LLMs) as part of the Automation & Asset Development & Deployment team. Build intelligent automation workflows and support scalable, secure AI deployments for infrastructure and application managed services use cases.

What you'll do

• Design, test, and optimize prompts for LLMs to support use cases which benefit the infra & application managed services.
• Build and maintain Python-based microservices and scripts for data processing, API integration, and model orchestration.
• Collaborate with SMEs to convert business requirements into GenAI-powered workflows, including chunking logic, token optimization, and schema transformation.
• Work with foundation models and APIs, including OpenAI, Vertex AI, and Claude Sonnet, to embed GenAI capabilities into enterprise platforms.
• Ensure all AI solutions comply with internal data privacy, PII masking, and security standards.
• Conduct A/B testing of prompts, evaluate model outputs, and iterate based on SME feedback.
• Maintain clear documentation of prompt strategies, model behaviours, and solution architectures.

What you'll need

• Strong proficiency in Python, including experience with REST APIs, data parsing, and automation scripting.
• Deep understanding of LLMs, prompt engineering, and GenAI frameworks, including LangChain and RAG pipelines.
• Familiarity with data modelling, SQL, and RDBMS concepts.
• Experience with agentic workflows, token optimization, and schema chunking.

Details

• Location: Gurugram; the source location line also states “Location Negotiable”.