Description

Architect and implement end-to-end generative AI solutions, from LLM integration to scalable enterprise deployment.

This role is on-site.

Responsibilities

• Design GenAI architectures using LLMs (OpenAI, Azure OpenAI, Google Gemini, Anthropic) and define governance frameworks.
• Implement RAG pipelines, prompt engineering, fine-tuning, and agentic AI systems with vector databases (Pinecone, FAISS, Weaviate, Chroma).
• Build scalable data ingestion, embedding, and semantic search pipelines using Python and ML frameworks.
• Deploy and manage AI models on cloud platforms (Azure, AWS, GCP) with CI/CD and MLOps practices.
• Collaborate with stakeholders to translate business use cases into technical solutions and mentor engineering teams.

Required Skills

• 12+ years of software engineering experience with strong proficiency in Python.
• Deep understanding of Transformer architectures, NLP concepts, and prompt evaluation techniques.
• Hands-on experience with LangChain, LlamaIndex, and Semantic Kernel.
• Experience with containerization (Docker, Kubernetes) and microservices architecture.
• Familiarity with REST APIs, system design, and DevOps/MLOps practices.
• Knowledge of cloud AI services: Azure OpenAI, AWS Bedrock, Google Vertex AI.
• Experience with Java and Spring Boot is required.

Preferred Skills

• Experience with Amazon Q and Kiro tools.
• Background in implementing responsible AI practices, including security and bias mitigation.

Key Skills

Education

Any Graduate