Software Engineer (AI)

About this role

Batch: 2019/2020/2021/2022. About the role: - Build and integrate memory systems that allow AI agents to maintain and leverage context effectively across interactions - Construct retrieval-augmented generation pipelines that connect large language models to live data sources and contextual information - Refine models through advanced prompt engineering, transfer learning approaches, and custom model development - Tune model efficiency and spending in live production settings - Manage deployment of models at scale on AWS, GCP, or Azure using Docker and Kubernetes for containerization - Partner with distributed teams and research staff across geographies in a remote environment that moves quickly Your technical toolkit: - Hugging Face for model handling and fine-tuning - LangChain for orchestrating language model workflows - OpenAI APIs for LLM integration - Vector databases including FAISS, Pinecone, and Weaviate - Container and orchestration platforms for production-grade deployment What we're looking for: - Minimum 4+ years working in artificial intelligence and machine learning, with substantial hands-on experience in generative AI systems and large language models - Demonstrated expertise in memory architectures, context management techniques, and retrieval-augmented generation implementation - A minimum of 2-3 years of backend software engineering work — this is essential for the position - Degree in computer science or related field, ideally from a Tier 1 institution