Description

Design and build scalable, cloud-native applications integrating Generative AI, LLMs, and vector databases.

This role is on-site.

Responsibilities

• Develop and maintain backend services and APIs with a focus on performance and reliability using Python.
• Integrate Azure OpenAI and LLMs to create business insights, executive summaries, and generative AI solutions.
• Perform automated data validation, anomaly detection, and quality analysis using Pandas and Polars.
• Implement CI/CD pipelines, automated testing, and DevOps best practices for deployment automation.
• Monitor and optimize application performance using logging, monitoring, and observability tools.

Required Skills

• 6–8 years of software development experience with strong proficiency in Python.
• Hands-on experience with Generative AI, LLMs, RAG architectures, and Vector Databases.
• Experience with Azure OpenAI and LangChain for building AI-driven applications.
• Proficiency in data manipulation libraries, specifically Pandas and Polars.
• Understanding of SLMs (Small Language Models) and LLM fine-tuning.
• Experience designing distributed and event-driven systems with high availability.
• Knowledge of infrastructure as code (Terraform, Pulumi) and containerization (Docker, Kubernetes).

Preferred Skills

• Experience deploying SLMs on edge or low-latency environments.
• Familiarity with polyglot persistence (SQL & NoSQL) and AI-assisted coding tools like GitHub Copilot.

Key Skills

Education

Any Graduate