• Understand, develop, & support deep math analytics in Explainable AI Engines • Build, evolve, verify, and validate data processing pipeline segments • Support scalable deployment of the AI • Integrate Explainable AI with LLM tools for Agentic AI experience • Collaborate with the cloud software team and occasionally with customers • Document Explainable AI for customer users and internal software developers

• Design, secure, extend, and customize system prompts (e.g., chat history, instructions, rules); • Evaluate the impact of prompt changes and continuously improve LLM usage scenarios while analyzing risks and benefits. • Design and optimize retrieval pipelines, including document chunking, embedding generation, and ranking strategies. • Build and maintain solutions using vector databases (e.g., FAISS, Weaviate, Pinecone) or Postgres with pgvector, to enable accurate and context-aware responses. • Implement advanced context window optimization, memory strategies, and token efficiency techniques to ensure scalable and cost-effective LLM interactions. • Evaluate new LLM releases, monitor response quality and consistency, and build automated evaluation pipelines to assess performance across use cases. • Design and implement prompt injection protection, output filtering, and policy enforcement mechanisms to ensure safe and compliant AI behavior in enterprise environments. • Develop and expose AI capabilities via scalable APIs, ensuring proper integration into existing systems and workflows. • Design and manage serving layers for LLM applications, addressing scaling strategies, latency considerations, and reliability in both cloud and on-prem environments. • Implement logging, monitoring, and alerting mechanisms to ensure visibility into system performance, usage patterns, and failures. • Develop prototype and production-level Python code to support AI features, ensuring reliability and maintainability aligned with product requirements. • Stay up to date with the latest techniques in reasoning, chaining, and context optimization; contribute to AI Labs community discussions and share findings with the Data Science team.

Please submit your resume in English and indicate your level of English. At Toloka, we connect smart, curious people from around the world with freelance online tasks that train and improve artificial intelligence. What we do The Toloka Annotators connects individuals with Generative AI projects from leading tech innovators. Our mission is to unlock the full potential of AI by involving real people from around the world in the development process. About the Role Annotation is what helps AI make sense of the world. As an annotator, you may be invited to take part in online projects such as rating AI-generated content, evaluating factual accuracy, or comparing responses - when projects are available. Responsibilities: - Carefully review provided data (text, images, or videos) - Label or classify content based on project guidelines - Identify and flag factually incorrect, sensitive, inappropriate, or unclear material Important note: This is project-based work. Tasks are available only when projects are active. You may be invited to one or more projects depending on your profile and current opportunities. Each project has its own compensation level based on scope and expertise required. On this project, AI trainers earn up to $18 per hour equivalent.

Please submit your resume in English and indicate your level of English. At Toloka, we connect smart, curious people from around the world with freelance online tasks that train and improve artificial intelligence. What we do The Toloka Annotators connects individuals with Generative AI projects from leading tech innovators. Our mission is to unlock the full potential of AI by involving real people from around the world in the development process. About the Role Annotation is what helps AI make sense of the world. As an annotator, you may be invited to take part in online projects such as rating AI-generated content, evaluating factual accuracy, or comparing responses - when projects are available. Responsibilities: - Carefully review provided data (text, images, or videos) - Label or classify content based on project guidelines - Identify and flag factually incorrect, sensitive, inappropriate, or unclear material Important note: This is project-based work. Tasks are available only when projects are active. You may be invited to one or more projects depending on your profile and current opportunities. Each project has its own compensation level based on scope and expertise required. On this project, AI trainers earn up to $18 per hour equivalent.