KMS Technology

Tóm tắt công việc

AI-Native Engineering Practice - Technical Ownership:

• Own and continuously evolve KMS's AI-native SDLC operating model at KMS: agent workflow designs, verification gates, context management standards, and eval frameworks
• Build and lead multi-agent systems using orchestration layers such as Claude Code, GitHub Copilot Workspace, Cursor, LangGraph, CrewAI, or equivalent — from prototype to production
• In collaboration with the Director of Engineering, contribute to and help maintain KMS's AI toolchain selection criteria — evaluating tools with engineering rigor, not hype — and publishing internal guidance on when AI helps and when it hurts
• Establish prompt engineering standards, agent evaluation (evals) loops, and AI output quality gates across the delivery organization

Capability & Standards Leadership (for Lead role)

• Prior experience in a lead, principal, or staff engineer role with demonstrated cross-team influence 
• Experience in outsourcing, consulting, or multi-client delivery environments
• Track record of building or leading an internal community of practice, guild, or AI adoption program
• Develop and continuously evolve KMS's AI-native SDLC playbook — standards, workflow templates, case studies, and guardrails that delivery teams can adopt immediately
• Design and lead internal upskilling programs (workshops, pairing) that move engineers from AI-assisted to AI-native working patterns
• Track the AI capability frontier — model improvements, new agent frameworks, emerging risks — and translate signals into timely updates to KMS's practices

Client Delivery (for Lead role)

• Work closely alongside KMS Delivery Teams — as an AI transformation advisor and execution partner — identifying the highest-value automation opportunities across the SDLC and coordinating with the team to bring them to life
• Design and deploy agent-orchestrated workflows tailored to each client's stack, team maturity, and delivery context — with measurable ROI
• Build business cases for AI-native adoption with clients and account managers, framing the value in terms of velocity, quality, and cost
• Represent KMS's AI-native engineering capabilities in client conversations, QBRs, and RFP responses — acting as a credible technical authority

General Requirements:

• 8+ years of professional software engineering, with a proven track record of leading technical initiatives that span multiple teams or systems 
• Fluent in English communication

Technical Environments: 

Core Engineering Foundation

• Deep hands-on experience across the full SDLC: from requirements and architecture through testing, deployment, and production operations 
• Demonstrated ability to lead technical direction — setting standards, reviewing architecture decisions, and influencing without direct authority
• Strong command of software architecture principles: system decomposition, API design, scalability, observability, and failure mode reasoning
• Proficiency in at least one primary language: Python, TypeScript/JavaScript, Java, .Net or Go — with experience across multiple layers of the stack

AI & Agentic Systems Fluency

• Proven, production-grade experience with AI coding agents as a core part of your daily workflow 
• Strong understanding of LLM API integration in production: context window management, latency and cost tradeoffs, model selection criteria, fallback strategies, and output reliability patterns
• Experience or strong interest in multi-agent orchestration patterns: task decomposition, agent communication, tool use, memory, and eval loops
• Working knowledge of RAG architectures, embedding strategies, and how to ground AI agents in domain-specific, proprietary knowledge bases
• Ability to design and run AI evals: you can define quality metrics, build evaluation datasets, detect regressions, and use quantitative signals to improve agent behaviour over time

Nice to have

• Experience with agentic frameworks: LangGraph, CrewAI, AutoGen, or similar orchestration patterns
• MLOps knowledge: model deployment, monitoring, drift detection, A/B testing in production
• Familiarity with AI security risks: prompt injection, adversarial inputs, data leakage in agentic contexts