Description

You will build, design, and deploy GenAI-powered applications using LLMs, embeddings, vector databases, and prompt engineering.

Responsibilities

• Build RAG applications and Agentic AI systems for autonomous task execution and multistep reasoning using LangChain and LangGraph.
• Design, develop, and deploy microservices-based enterprise integrations for GenAI features.
• Implement test cases and datasets to ensure model accuracy across classification, regression, and reinforcement learning models.
• Collaborate with cross-functional teams to integrate AI solutions into existing architectures.
• Maintain SDLC best practices including requirements, design, testing, and deployment.

Required Skills

• Strong programming skills in Python, including LangChain, LangGraph, and Transformers.
• Experience with OpenAI APIs and building RAG pipelines.
• Solid understanding of software engineering principles and design patterns.
• Proficiency with SDLC tools: JIRA, Git, Bitbucket/GitHub, Jenkins, and SonarQube.
• Knowledge of ML/AI models including CNNs and classification/regression techniques.
• Experience with RESTful services, API design (Swagger/OpenAPI), and microservices architecture.
• 5+ years of professional experience.

Preferred Skills

• Experience with DevOps tools: Docker, Kubernetes, and CI/CD pipelines.
• Familiarity with infrastructure-as-code and automated testing frameworks.
• Knowledge of code quality metrics, unit testing (Pytest), and code coverage.

Key Skills

Education

Bachelor's degree