Description

You will design and build scalable generative AI applications, owning the end-to-end lifecycle of LLMs from prompt engineering and fine-tuning to deployment and monitoring.

This role is on-site.

Responsibilities

• Build GenAI applications and RAG systems using LangChain, vector databases, and embedding models.
• Design and deploy AI solutions on Azure (OpenAI, Machine Learning, Functions) and integrate with AWS SageMaker and Bedrock.
• Develop and fine-tune LLMs and ML models for classification, prediction, and decision support tasks.
• Integrate AI systems with enterprise data platforms, APIs, and business workflows to ensure seamless operation.
• Optimize model performance through advanced prompting techniques (zero-shot, few-shot, chain of thought) and continuous monitoring.

Required Skills

• 5+ years of experience in software engineering or machine learning roles.
• Strong proficiency in Python and frameworks like Pandas, NumPy, and FastAPI.
• Hands-on experience with Generative AI tools: LangChain, Azure OpenAI, AWS SageMaker, and Vector Databases.
• Deep understanding of RAG architectures, LLMs, and machine learning algorithms.
• Experience deploying models using serverless execution and cloud infrastructure (Azure/AWS).
• Familiarity with Hugging Face, Pydantic, and model optimization techniques.
• Ability to connect models to data sources and orchestration platforms.

Preferred Skills

• Solid foundation in ML training pipelines, evaluation techniques, and tokenization.
• Experience with Snowflake and enterprise data integration.
• Knowledge of security protocols and compliance standards for AI systems.

Key Skills

Education

Any Graduate