• Design and develop intelligent agents using Python and Autogen framework (or similar frameworks) • Collaborate with AI/ML teams to integrate LLMs (e.g., OpenAI, Anthropic, Google, etc.) into multi-agent workflows • Develop and maintain cloud-native applications and services (Azure / AWS / GCP) • Create robust APIs and integrate them with external/internal systems • Implement data ingestion, transformation, and storage logic using SQL, NoSQL, Columnar and Vector DBs • Support system scalability, performance, and maintainability using clean architecture principles • Contribute to agent orchestration logic, tool integrations, and interaction flows • Work closely with the Solutions Architect to align implementation with architecture vision • Write tests, maintain documentation, and participate in code reviews

• Design and develop intelligent agents using Python and Autogen framework (or similar frameworks) • Collaborate with AI/ML teams to integrate LLMs (e.g., OpenAI, Anthropic, Google, etc.) into multi-agent workflows • Develop and maintain cloud-native applications and services (Azure / AWS / GCP) • Create robust APIs and integrate them with external/internal systems • Implement data ingestion, transformation, and storage logic using SQL, NoSQL, Columnar and Vector DBs • Support system scalability, performance, and maintainability using clean architecture principles • Contribute to agent orchestration logic, tool integrations, and interaction flows • Work closely with the Solutions Architect to align implementation with architecture vision • Write tests, maintain documentation, and participate in code reviews

• Lead the technical design and architecture of AI agent platforms and multi-agent workflows built on LangChain and LangGraph. • Hands-on development of AI agents. • Integrate LLMs from providers such as OpenAI, Anthropic, and Azure OpenAI into production-grade agent pipelines. • Build and optimize CI/CD, containerization, and infrastructure-as-code practices for the team. • Establish and maintain AI observability across agent systems - tracing execution paths, monitoring performance, tracking costs, and surfacing anomalies. • Mentor and guide engineers through code reviews, architectural discussions, and knowledge sharing sessions. • Collaborate with product managers, solution architects, and stakeholders to align technical implementation with business objectives. • Ensure system reliability, scalability, and maintainability through clean architecture, automated testing, and deployment best practices. • Contribute to defining engineering standards, development workflows, and documentation practices across the team. • Contribute to technical solutions for AI-oriented proposals during pre-sale cycles

• Qualified lead growth to publitas.com from organic and AI-search channels - this is the metric you're measured on. • SEO performance: technical health, rankings, and content quality on the pages that drive pipeline. • GEO/AEO: getting Publitas cited in AI-generated answers for our category, and measuring citation share over time. • Lead attribution from day one: instrumenting organic and AI-referred traffic through to qualified leads, so we can prove what's working rather than report traffic in isolation. • The automation: designing and building the system that scales monitoring, content, and optimization.