AI Engineer - AWS

Key Responsibilities:

• Design and develop RAG-based pipelines using vector databases and LangChain for enterprise-scale applications.
• Build, fine-tune, and optimize LLM-powered solutions, including prompt engineering and model evaluation for domain-specific tasks.
• Integrate and deploy AI solutions on AWS Bedrock and Azure AI platforms.
• Develop and maintain knowledge graphs to support intelligent querying and reasoning in GenAI solutions.
• Implement agentic frameworks to enable autonomous AI workflows and decision-making.
• Collaborate with cross-functional teams to align AI initiatives with business goals.
• Ensure scalability, performance, security, and compliance of AI applications in enterprise environments.
• Stay updated on the latest GenAI and LLM advancements to continuously improve solution capabilities.

Required Skills & Experience:

• 5–7 years of hands-on experience in AI/ML, with a focus on Generative AI.
• Strong experience with LangChain or similar orchestration frameworks.
• Proven experience with RAG pipelines and vector databases (Pinecone, FAISS, Weaviate, Milvus, ChromaDB).
• Experience integrating and deploying solutions on AWS Bedrock and Azure AI services.
• Working knowledge of Knowledge Graphs (Neo4j, RDF, Graph DBs) and semantic search.
• Hands-on experience in LLM fine-tuning (OpenAI, Anthropic, HuggingFace models) for domain-specific use cases.
• Proficiency in Python and modern AI development frameworks.
• Experience building enterprise-grade GenAI or agentic applications.
• Familiarity with CI/CD for ML/AI pipelines is a plus.