Job Title:
Gen Ai
Location:
PAN India
Experience:
7 - 15 Years
Role Overview
We are seeking a skilled
Gen AI
with hands-on experience in
Large Language Models (LLMs) and generative AI solutions
. The engineer will be responsible for
implementing, deploying, and monitoring LLM-based AI solutions
on Azure, integrating them into enterprise workflows, and ensuring performance, reliability, and scalability.The role requires expertise in
prompt engineering, agentic AI frameworks, retrieval-augmented generation (RAG), and AI service integration
, along with strong programming skills in Python and familiarity with Microsoft Azure AI services.
Key Responsibilities
- LLM Implementation & Deployment
- Implement and deploy LLM-based AI solutions for enterprise use cases such as FinOps, CostOps, and other business-critical applications.
- Validate, monitor, and optimize AI model performance and relevance in production environments.
- Prompt Engineering & Optimization
- Design and implement role-based, context-aware, and instruction-tuned prompts for AI agents.
- Optimize prompts for accuracy, relevance, and performance of generative AI outputs.
- Programming & Integration
- Develop and maintain Python applications using LangChain, MCP, OpenAI SDK, and related AI libraries.
- Integrate LLM and AI services into enterprise applications via REST APIs and SDKs.
- Retrieval-Augmented Generation (RAG)
- Build data ingestion pipelines to enhance model responses using enterprise data.
- Implement semantic search using vector databases and embedding models to support RAG frameworks.
- AI Agent Experience
- Work with agentic AI frameworks (e.g., LangGraph) to design autonomous AI agents.
- Implement workflows and pipelines for multi-agent AI solutions.
- Monitoring & Performance Management
- Continuously monitor deployed LLM solutions for performance, reliability, and cost optimization.
- Troubleshoot and resolve production issues efficiently.
Required Skills & Qualifications
- Hands-on experience with generative AI models such as OpenAI, LLaMA, Claude, etc.
- Strong understanding of prompt engineering (role-based, context-aware, instruction-tuned).
- Expertise in Python programming, LangChain, MCP, and OpenAI SDK.
- Experience in RAG (Retrieval-Augmented Generation), vector databases, and embedding models.
- Familiarity with agentic AI frameworks such as LangGraph.
- Experience integrating AI solutions into enterprise applications via APIs and SDKs.
- Knowledge of Azure AI services and cloud deployment best practices.
Preferred Skills
- Exposure to multi-agent AI workflows and autonomous agent orchestration.
- Hands-on experience in enterprise-scale AI deployment and monitoring.
- Understanding of AI safety, governance, and ethical considerations.
Soft Skills
- Strong analytical and problem-solving skills.
- Excellent communication and collaboration abilities.
- Ability to work in dynamic, fast-paced environments with flexible priorities.
- Commitment to continuous learning and staying up-to-date with emerging AI technologies.