Lead Software Engineer – AI

Job Summary The Lead Software Engineer – AI & Agentic Engineering is responsible for the overall technical direction, architecture, engineering standards, and technology governance across all AICC products, and is the technical owner of the shared product platform components used by multiple products. This is a cross-product technical leadership role. The Lead Software Engineer does not manage each engineering team directly but provides technical leadership, architecture guidance, engineering standards, and technical coaching to Senior Software Engineers and development teams across multiple products. The Lead Software Engineer is the formal technical counterpart to the AI Division and to DevOps: defining how products consume AI capabilities, agreeing capability contracts, and defining production-readiness standards. A key responsibility of this role is to drive the adoption of Agentic Engineering, enabling engineering teams to effectively use AI coding agents and engineering agents while maintaining high standards of architecture, security, quality, and maintainability. This is a hands-on technical leadership role, not an AI research position. Deep model work is owned by the AI Division. Decision Rights To function without direct reporting lines, the role holds the following explicit decision rights:
• Approval authority over architecture decisions recorded as Architecture Decision Records (ADRs) and technical RFCs.
• Authorities block a release on architecture, security, or production-readiness grounds, escalating to the Head of AICC Product when a business trade-off is required.
• Ownership of engineering standards that all product teams are required to follow.
• Ownership of the shared product platform backlog, prioritized jointly with the Head of AICC Product.

Key Responsibilities
Technical Strategy & Architecture
• Own the overall technical direction across AICC products.
• Define and maintain reference architectures and engineering standards.
• Lead major architecture and system design decisions; run the architecture review forum.
• Establish technical guardrails while allowing teams sufficient implementation autonomy.
• Review critical architecture decisions and cross-product technical dependencies. Shared Product Platform Ownership Own the technical direction and quality of components shared across products, including but not limited to:
• LLM gateway (routing, fallback, rate limiting, cost tracking, prompt/version management)
• Knowledge base / RAG pipeline used by multiple products
• Telephony and real-time media layer (SIP, WebRTC, streaming audio, ASR/TTS integration)
• Conversation/session state, event streaming, and integration framework
• Product-level AI evaluation framework and observability Decide, together with the AI Division, whether a needed capability is built by the AI Division, built as an application-level component in the Product OC, or deferred. Software Architecture Provide technical leadership in distributed systems, microservices, REST and WebSocket APIs, event-driven architecture, real-time and high-concurrency systems, cloud-native and on-premise deployable architecture, data architecture, scalability, high availability, resilience, security, and observability. Evaluate technical trade-offs across performance, complexity, cost, scalability, maintainability, deployment model (SaaS vs on-premise), and time-to-market. AI Application Integration Architecture Define how AICC products consume AI capabilities provided by the AI Division and third-party providers:
• Capability contracts and API design between products and AI services
• Latency budgets for real-time voice and agent-assist use cases
• Fallback and degradation strategies (model unavailability, timeout, quality guardrails)
• Inference cost management and cost-per-conversation observability
• Application-level guardrails, prompt injection defense, PII handling in prompts, transcripts, and logs
• Application-level AI observability (quality drift, latency, error, cost)
• Product-level evaluation architecture (golden sets, regression harness, LLM-as-judge where appropriate) Work with the AI Division on model selection constraints, self-hosted vs API deployment for on-premise customers, and language-specific (Thai) quality requirements. Ensure AI solutions are production-ready with appropriate consideration for latency, accuracy, hallucination, security, reliability, inference cost, scalability, and observability. Agentic Engineering Leadership Drive the company's engineering transformation toward Agentic Engineering:
• Define best practices for Human + AI engineering workflows.
• Evaluate and recommend AI coding agents and engineering tools.
• Establish standards for AI-generated code, including review, testing, and validation requirements.
• Create reusable engineering workflows, prompts, skills, tools, and agent patterns.
• Guide engineers on task decomposition for coding agents.
• Establish security and governance practices for AI-assisted development (secrets, data exposure to external tools, license compliance), aligned with Compliance / Security.
• Monitor engineering productivity and software quality; prevent uncontrolled generation of technical debt.
• Coach Senior Engineers on supervising and collaborating with engineering agents. Engineering Governance
• Establish coding and architecture standards and development best practices.
• Conduct architecture reviews and technical design reviews.
• Guide engineering teams on technical debt management.
• Define standards for CI/CD, observability, deployment, and production readiness in agreement with DevOps.
• Ensure compliance and security requirements are implemented as technical controls, in agreement with Compliance / Security. Technical Coaching
• Mentor Senior Software Engineers across product teams.
• Support engineers with difficult technical and architecture decisions.
• Develop engineering capabilities across the organization; facilitate technical knowledge sharing.
• Promote engineering ownership and continuous improvement. Required Qualifications
• 8+ years of software engineering experience with a strong hands-on development background.
• Experience as Technical Lead, Software Architect, Principal Engineer, Staff Engineer, or similar.
• Strong understanding of software architecture and distributed systems.
• Experience with cloud-native technologies, containers, and CI/CD.
• Strong understanding of AI application architecture and integration of LLM-based capabilities into production systems.
• Experience using or integrating modern AI engineering tools and coding agents.
• Strong analytical and technical problem-solving skills.
• Ability to influence and drive decisions without direct authority. Preferred Qualifications
• LLM application development, RAG, AI Agents / Agentic AI
• AI-assisted software development at team or organization scale
• Kubernetes, on-premise deployment, GPU / AI inference infrastructure
• Real-time systems, telephony, WebRTC, streaming audio
• ASR / TTS integration
• Enterprise software; Contact Center or Customer Experience systems
• Security and data protection practices (PDPA or equivalent)
• Contact Center domain knowledge is an advantage but not required.