Responsibilities
- Design and develop multi-agent systems with focus on agent coordination, task delegation, and tool integration.
- Create scalable RAG systems using vector databases, embedding workflows, and data segmentation techniques.
- Enhance and integrate MCP tools to enable reliable model-to-tool communication and automate workflows.
- Lead the creation of AI-powered features, proofs of concept, and production-grade solutions using hosted or self-deployed LLMs.
- Develop and refine prompt engineering strategies, including prompt sequences, agent cycles, and iterative refinement processes.
- Establish frameworks for evaluating agent performance, including scenario-based testing and regression checks.
- Build automated testing systems to assess LLM accuracy, consistency, hallucination mitigation, and operational metrics.
- Advance system capabilities through A/B testing, reinforcement modeling, and continuous feedback integration.
- Track and optimize key system indicators such as speed, cost-efficiency, uptime, and fault tolerance.
- Guide engineers specializing in artificial intelligence, data processing, and backend development.
- Partner with product leads, research teams, and other departments to ensure technical direction supports business goals.
- Perform code reviews, uphold coding standards, and ensure adherence to architectural guidelines.
- Manage technical planning, sprint cycles, and delivery timelines for engineering initiatives.
- Deploy and manage AI services on cloud infrastructure using AWS, GCP, or Azure platforms.
- Integrate vector database technologies such as Pinecone, Weaviate, or Elasticsearch.
- Develop APIs and microservices to deliver AI functionality to internal teams and external users.
- Ensure data ingestion and retrieval pipelines are secure, compliant, and performant.
- Oversee the design and implementation of agent orchestration and interaction patterns.
- Architect and fine-tune systems for prompt chaining and iterative output refinement.
- Support the deployment of self-hosted and API-based language models in production environments.
- Maintain robust monitoring and optimization protocols for AI system performance.
Work Arrangement
Hybrid
Team
Team consists of over 1,000 employees.
