VAS is seeking an AI Engineer to lead building of scalable real-time production grade applications that use AI/ML models. This is a strategic, hands-on position for an experienced technical leader who has a track record of shipping AI-enhanced customer applications and tooling used by engineering teams.
This role will be focused on embedding LLMs, agent-based systems, and automation into core development workflows—boosting productivity, reducing manual toil, and accelerating delivery, essentially transforming how our engineers build, test, and ship software.
Responsibilities
- Understand customer challenges and how integrating AI capabilities can help lead to solutions that have AI as a differentiator.
- Identify opportunities to apply AI for efficiency, growth, and customer value.
- Drive awareness of AI capabilities and demonstrate how it can address customer needs, improve efficiency, reduce costs, and drive growth.
- Drive transformation from AI-Ad Hoc to AI-Native engineering practices.
- Serve as the AI technical SME, conduct R&D (research and development) to meet the needs of our AI strategy.
- Continuously assess emerging AI tools and make data-driven recommendations.
- Measure & Accelerate Adoption: Establish KPIs, track progress from the current to 100% adoption, implement interventions to accelerate uptake and communicate impact.
- Build Center of Excellence: Create forums for knowledge sharing, celebrate wins, and foster peer-to-peer learning.
- Establish AI governance frameworks and guardrails covering compliance, security, privacy, and ethical AI practices, and embed them into development workflows.
- Architect and implement LLM agents.
- Build composable, tool-augmented reasoning chains (e.g., RAG, CoT, ReAct, planner-executor).
- Integrate vector databases and knowledge graphs to support retrieval-augmented generation (RAG).
- Design and maintain high-quality prompt strategies for robustness and reliability.
- Develop and maintain scalable APIs, supporting synchronous and asynchronous agent execution.
- Integrate Model Context Protocol (MCP) to enable secure and structured access to external data and tools within agent workflows.
- Implement state tracking, context-aware input dispatch, and modular plugin integration within the control plane.
- Build unit and behavioral tests for agents, tools, and workflows.
- Develop tooling for trace analysis, agent state debugging, and hallucination tracking.
- Compare and benchmark agent orchestration frameworks for trade-offs in speed, reliability, and usability.
- Integrate, deploy, fine tune and monitor models in production using cloud providers.
- Set up agent logging, observability dashboards, and recovery workflows.
- Collaborate with front-end developers or build user-facing components using React, TypeScript.