We are seeking a highly skilled Applied AI Engineer with a strong background in Python development, Natural Language Processing (NLP), and machine learning. The ideal candidate will have experience working with large language models (LLMs), including prompt chaining, RAG (Retrieval-Augmented Generation) techniques, and workflow orchestration, as well as a solid grasp of AWS-based DevOps, SQL, and REST APIs. Familiarity with graph databases and similarity search strategies is a plus.

You'll collaborate with cross-functional teams to design, implement, and scale intelligent systems that extract insights from unstructured text and drive decision-making across the business.

• Design and develop scalable NLP and LLM-based solutions using Python.
• Build and maintain LLM prompt chains, workflows, and retrieval mechanisms.
• Collaborate on model evaluation, fine-tuning, and RAG pipeline implementation.
• Integrate AI capabilities with external APIs and structured data sources.
• Develop and deploy machine learning models with a focus on production readiness.
• Optimize data workflows and DevOps pipelines on AWS.
• Write performant, maintainable code and contribute to engineering best practices.
• Interface with SQL and NoSQL databases, including basic work with graph databases.
• Stay up to date with emerging trends in AI/ML, NLP, and LLM research.

• Expert-level proficiency in Python, especially for AI/ML applications.
• Strong experience in Natural Language Processing (NLP) techniques and libraries.
• Solid experience with machine learning frameworks (e.g., scikit-learn, PyTorch, or TensorFlow).
• Experience working with or integrating LLM workflows and prompt chaining.
• Proficiency in SQL and familiarity with data modeling.
• Hands-on experience with AWS DevOps tools and environments (e.g., Lambda, ECS, S3, CloudFormation).
• Strong understanding of REST APIs and integration best practices.
• Familiarity with graph databases (e.g., Neo4j, Amazon Neptune) and their use in AI systems.
• Awareness of similarity search, vector databases, and RAG-style architectures.

• Experience with RAG pipelines, vector stores (e.g., FAISS, Weaviate, Pinecone).
• Understanding of trade-offs between structured vs. unstructured data extraction approaches.
• Previous experience deploying AI solutions in production environments.
• Passion for emerging AI applications and pragmatic problem-solving.