Senior GenAI / LLM Application Developer

Miracle Software Systems, Inc.; India; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

A technology services company in India is seeking a Senior GenAI / LLM Application Developer to design and develop AI-powered applications and workflows. The role requires proficiency in Python and various LLM frameworks such as LangChain and LangGraph. Responsibilities include integrating AI solutions with enterprise systems and ensuring the responsible use of AI technologies. Ideal candidates will have experience in developing intelligent task execution systems and optimizing performance and cost of inference.

Qualifications

• Experience designing AI applications using Python.
• Proficiency with LLM frameworks.
• Knowledge of workflow management tools.
• Ability to integrate AI solutions with APIs.

Responsibilities

• Design and develop AI-powered applications using Python.
• Build and orchestrate LLM workflows with LangChain and LangGraph.
• Develop AI agents for interaction with enterprise tools.
• Integrate LLM models with enterprise systems.
• Implement monitoring and evaluation for responsible AI usage.

Skills

Python

LLM frameworks

LangChain

LangGraph

REST APIs

microservices

model performance optimization

Job description

Senior GenAI / LLM Application Developer

• Design and develop AI-powered applications using Python and modern LLM frameworks, ensuring production readiness and architectural alignment.
• Build and orchestrate LLM workflows using LangChain and LangGraph with a focus on agent orchestration and workflow management.
• Develop AI agents and multi-agent systems that interact with enterprise tools, APIs, and data platforms for intelligent task execution.
• Integrate LLM models such as OpenAI GPT, Claude, Llama, or open-source alternatives with a focus on reliability and maintainability.
• Implement Model Context Protocol to enable structured interaction between LLMs and enterprise systems with consistent context handling.
• Design prompt engineering strategies and structured output pipelines to improve response quality and control model behavior.
• Build and optimize RAG pipelines using vector databases to support context-aware retrieval and knowledge-driven applications.
• Integrate AI solutions with REST APIs and microservices, ensuring seamless data exchange and workflow orchestration across systems.
• Implement monitoring, evaluation, and guardrails to ensure responsible AI usage.
• Optimize inference performance and cost through efficient architecture and workload management.

Applicants are considered for employment without attention to or discrimination against race, color, religion, sex, sexual orientation, gender identity, national origin, veteran or disability status. All employment is decided on the basis of qualifications, merit and business need.