Roles & Responsibilities

• Design and deploy scalable AI applications utilizing Amazon Bedrock, OpenAI, or Hugging Face.
• Build and optimize RAG pipelines for document understanding, summarization, and contextual search.
• Implement Agentic AI systems to handle complex, autonomous workflows and decision trees.
• Extract, preprocess, and vectorize data from unstructured sources to enhance model accuracy and retrieval quality.
• Leverage vector stores such as OpenSearch, FAISS, or Pinecone for efficient semantic search.
• Develop and expose AI capabilities via RESTful APIs using AWS ECS, Lambda, and other cloud-native services.
• Optimize model performance through fine-tuning, caching, and low-latency inference strategies.
• Lead Proof-of-Concept (PoC) projects to validate innovative AI solutions.
• Collaborate cross-functionally with ML engineers, data engineers, and cloud architects to ensure high-quality delivery and innovation.

Required Skills/Qualifications

• 8+ years of experience in software engineering, with a strong focus on AI and cloud-native technologies.
• Hands-on expertise with LLMs, Generative AI models, and AI search systems.
• In-depth knowledge of Amazon Bedrock, or equivalent platforms such as OpenAI and Hugging Face.
• Solid experience implementing Retrieval-Augmented Generation (RAG) pipelines and knowledge retrieval frameworks.
• Experience building Agentic AI workflows for autonomous decision-making and task execution.
• Strong programming skills in Python or similar AI-focused languages.
• Proven ability to deploy and manage services via AWS ECS, Lambda, and other serverless architectures.
• A mindset focused on experimentation, rapid iteration, and performance tuning.

Posted By