• Design, develop, and maintain scalable backend systems and services • Build and manage RESTful and/or GraphQL APIs • Integrate AI/ML models and third-party AI services into applications • Handle database design, optimization, and data processing • Collaborate with frontend developers, product managers, and other stakeholders • Ensure performance, security, and scalability of backend systems • Write clean, maintainable, and well-documented code • Troubleshoot and debug issues across the system

• Design, develop, and maintain backend systems in Golang within a microservices architecture • Build and scale APIs and backend services on AWS and Docker • Work with PostgreSQL, MongoDB, and Snowflake • Contribute to frontend development using React and TypeScript • Follow engineering best practices: clean code, testing, security, scalability • Collaborate with business, design, and product teams • Work in Agile, owning tasks from design to deployment • Support CI/CD and IaC initiatives as needed

• Work with PostgreSQL and vector extensions or OpenSearch/ElasticSearch for vectorized data storage supporting RAG pipelines • Design and build AI agents and multi-agent systems using frameworks such as LangGraph and platforms like AWS Bedrock • Evaluate and implement efficient Generative AI solutions using direct API integrations when appropriate • Develop scalable architectures for complex AI workflows and agent-based systems • Apply best practices in testing, CI/CD, and observability • Lead system design and architectural decisions ensuring scalability and reliability • Mentor engineers and conduct code reviews • Troubleshoot technical and infrastructure issues and ensure optimal performance • Drive innovation and deliver impactful AI solutions in a distributed global team

• Working on critical backend services and shared platform components that support ingestion, request routing, caching, reliability, and production operations. • Profiling bottlenecks and improving performance in critical paths. • Reducing operational toil by turning manual or fragile processes into repeatable, well-owned systems. • Helping with incident prevention, operational reviews, and follow-up work after reliability issues. • Keeping key dependencies current and operationally safe. • Improving the observability stack: telemetry, dashboards, alerting, and long-term visibility into system health. • Working on Kubernetes lifecycle tasks, cluster-level infrastructure, or deployment safety. • Improving CI/CD foundations so teams can ship and operate changes with more confidence. • Making development and test environments faster, more stable, and more useful for engineering teams.