-
Architect, code, and deploy custom AI agents and automation solutions using Python and relevant frameworks, such as LangChain and AutoGen, to solve complex business challenges within Global Enablement.
-
Develop and maintain backend logic and microservices required to support AI workflows, ensuring high availability and scalability of deployed agents.
-
Build custom retrieval augmented generation (RAG) systems by integrating large language models (LLMs) with PostgreSQL with pgvector and vector databases such as Pinecone and Weaviate, enabling secure interaction with proprietary data and approved content.
-
Write clean, maintainable, and efficient code for content generation, localization, and multimedia processing automations, adhering to software development best practices, including version control, code reviews, and testing.
-
Develop complete AI applications, including intuitive user interfaces, backend services, and secure integrations for internal and external users.
-
Implement conversation management, context retention, structured outputs, and tool calling to support interactive learning, guidance, and multi step workflows.
-
Evaluate and integrate conversational AI, speech recognition, speech generation, interactive avatars, and multilingual capabilities.
-
Build self service tools and AI supported workflows in partnership with subject matter experts, incorporating appropriate review and approval steps.
-
Design and implement secure RESTful API integrations to connect AI agents with business systems, learning and sales enablement platforms, knowledge repositories, and third party platforms.
-
Develop reusable code libraries, API wrappers, and solution frameworks to accelerate technical development across Global Enablement and ensure consistency in the codebase.
-
Collaborate with IT and GenAI platform teams to ensure departmental solutions align with company infrastructure and technology standards, leveraging cloud resources such as Google Vertex AI, Azure, and AWS effectively.
-
Develop knowledge ingestion and synchronization processes to keep connected content current, approved, and appropriate for its intended audience.
-
Implement authentication, authorization, and role based access controls for internal, partner, and customer facing applications.
-
Design solutions that support future integrations and additional enablement use cases without unnecessary duplication or redevelopment.
-
Implement code level security measures to ensure agents handling sensitive information, including internal documents and customer data, adhere to data privacy and responsible AI guardrails.
-
Establish continuous integration and continuous deployment (CI/CD) pipelines for testing and deploying AI agents, ensuring rigorous quality control and risk mitigation before production release.
-
Monitor technical performance metrics, including latency, token usage, and error rates, and optimize code to ensure cost efficiency and response quality.
-
Establish AI evaluation processes to test answer accuracy, retrieval quality, relevance, and appropriate handling of unsupported requests.
-
Implement safeguards against unauthorized information access, prompt injection, and unintended actions, including human approval and escalation where appropriate.
-
Maintain separation of internal, partner, and customer facing content, with appropriate controls to protect information across users and organizations.
-
Maintain deployed solutions through monitoring, troubleshooting, updates, and continuous improvement.
-
Document deployment procedures, support requirements, and operational handover processes to ensure continuity.
-
Translate complex business requirements from Global Enablement stakeholders into detailed technical specifications and architecture designs, supporting revenue generation, sales readiness, training effectiveness, and operational efficiency.
-
Conduct technical feasibility assessments on proposed use cases to determine whether they require custom code, existing platform configuration, or a combination of approaches.
-
Research and prototype emerging AI technologies, including new LLM releases and agentic frameworks, to maintain an effective and current technical stack for Global Enablement.
-
Partner with subject matter experts to translate specialized knowledge, learning objectives, and business processes into AI applications.
-
Collaborate with experts and end users to validate accuracy, instructional quality, usability, and effectiveness.
-
Define clear scopes, delivery phases, dependencies, and success criteria, communicating technical risks and tradeoffs to stakeholders.
-
Identify opportunities to automate repetitive work and create self service experiences across enablement teams, selecting AI or conventional automation as appropriate.
-
Evaluate opportunities to consolidate or replace existing applications with AI enabled solutions, considering functionality, cost, security, migration requirements, and ongoing support.
-
Measure solution impact through adoption, time saved, quality improvements, operating costs, and contribution to agreed enablement outcomes.
-
Bachelor’s degree in Computer Science, Data Science, Engineering, Artificial Intelligence, or a related quantitative field; Master’s degree preferred.
-
3–5 years of proven experience in AI/ML, Data Science, or software engineering roles with a focus on building and deploying intelligent systems or automation.
-
Strong proficiency in Python (including pandas and asynchronous programming) and working proficiency in JavaScript or TypeScript for user-facing applications.
-
Hands-on experience building multi-step agentic workflows with code-first frameworks such as LangChain, AutoGen, or CrewAI, and integrating LLM APIs such as OpenAI, Gemini, and Anthropic.
-
Demonstrated experience designing RAG pipelines using PostgreSQL with pgvector and vector databases or search libraries such as Pinecone, Weaviate, and FAISS.
-
Experience deploying applications in Google Cloud (Vertex AI, Cloud Functions), with solid knowledge of Git, testing, CI/CD, RESTful APIs, and secure coding practices.
-
Professional certifications in Google Cloud, Azure, AWS, or specific AI technologies, and experience with speech, avatar, or multilingual capabilities, are considered an asset.