Senior GenAI Engineer — AI Enablement & Agentic Systems-1

Samsung Electronics•New York, NY

1d•$140,000 - $170,000

About The Position

Samsung Ads focuses on enabling brands to connect with Samsung audiences across all devices. As an international company, Engineers at Samsung work on big complex projects with stakeholders and teams located around the globe. Our purpose is to deliver unparalleled results for our customers. Samsung Ads uniquely transforms the advertising landscape by using comprehensive data to build the world’s most intelligent connected audience platform. We deliver on Samsung Electronics’ 51-year commitment to excellence through smart, easy, effective advertising solutions to make advanced video advertising work.

Requirements

3+ years of hands-on experience with Generative AI tools and platforms, with a proven track record of delivering successful productivity or automation projects adopted by real users.
5+ years of experience in IT, automation, systems engineering, or a related technical role.
Proven experience delivering at least one end-to-end production deployment of a GenAI or agentic AI system in an enterprise environment — not just prototypes or POCs, but solutions actively used by business teams.
Strong hands-on proficiency with AWS Bedrock, Anthropic Claude (API, Claude Code, prompt engineering), and open-source AI tooling.
Demonstrated experience designing agentic AI workflows — including multi-agent orchestration, tool-use patterns, autonomous task execution, and deterministic execution patterns suitable for enterprise environments.
Experience with agentic AI frameworks and protocols such as Model Context Protocol (MCP), LangGraph, Claude Agent SDK, Amazon Bedrock Agents, CrewAI, or equivalent orchestration tools for building autonomous, multi-step AI workflows.
Understanding of agentic design patterns: reflection, planning, tool use, multi-agent collaboration, human-in-the-loop checkpoints, and error recovery strategies.
Working experience with RAG architectures, vector databases, embeddings, and self-hosted AI knowledge base platforms (e.g., AnythingLLM).
Proficiency in Python for scripting, automation, and AI tool integration.
Strong understanding of data classification frameworks, LLM-specific risks (data leakage, prompt injection, hallucination, unintended autonomous actions), and corporate security policies in a multinational enterprise environment.
Experience working with non-technical stakeholders and translating business needs into technical solutions.
A solution-oriented, opinionated approach — you have a clear point of view on what works, what scales, and what’s hype.
Highly organized and able to manage multiple priorities in a fast-paced environment.
Strong communication skills and the ability to convey AI capabilities and limitations to any audience.
Bachelor’s degree in Computer Science, Information Technology, or related field (or equivalent practical experience).

Nice To Haves

Experience with Model Context Protocol (MCP) for building tool-integrated AI agents at scale.
Experience integrating AI workflows with enterprise business systems (Salesforce, SAP, ServiceNow, Workday, or similar).
Background in Ad Tech or experience working in a digital advertising environment.
Familiarity with change management frameworks and delivering training/enablement programs at scale.
Experience navigating multinational corporate governance structures (especially APAC-headquartered companies).
Relevant certifications: AWS AI Practitioner, AWS ML Specialty, Anthropic Claude certification, or equivalent.
Experience building or managing AI Centers of Excellence or similar enablement functions.
Fluency in Korean.

Responsibilities

Design, build, and deploy GenAI-powered automation and productivity solutions for business teams across Sales, Marketing, Finance, HR, Legal, and Operations.
Architect and implement complex agentic workflows that enable AI agents to autonomously handle multi-step business processes — including task decomposition, tool orchestration, decision-making loops, and human-in-the-loop checkpoints where required.
Design and maintain multi-agent orchestration patterns, where specialized AI agents collaborate on complex tasks such as document analysis, research synthesis, data transformation, and cross-system process automation.
Serve as the primary hands-on technical resource for our AI tooling ecosystem, including AWS Bedrock, Claude, AnythingLLM, and our homegrown GenAI platform built on open-source tools.
Identify high-impact use cases through direct engagement with business stakeholders, translating pain points into practical AI-driven workflows — with a specific focus on processes that benefit from autonomous, adaptive execution rather than simple prompt-response interactions.
Build and maintain custom AI agents, prompt chains, RAG pipelines, and integrations tailored to departmental needs.
Integrate agentic AI workflows with existing enterprise applications and business systems (e.g., CRM, HRIS, finance tools, collaboration platforms) to enable end-to-end process automation across departments.
Define guardrails, escalation paths, and human oversight mechanisms for agentic workflows to ensure autonomous AI actions remain safe, auditable, and aligned with Samsung’s internal policies.
Develop evaluation frameworks for AI tools and agentic systems based on production requirements — including accuracy benchmarks, latency, cost-per-task, and compliance criteria — not vendor demos.
Evaluate and recommend new AI tools and vendors in collaboration with the Architecture team, including hands-on proof-of-concepts to support build-vs-buy decisions.
Ensure every AI solution deployed adheres to Samsung’s internal security and privacy policies, including data classification requirements mandated by HQ (South Korea).
Proactively assess data exposure risks of any AI tool or workflow before deployment and maintain a clear inventory of all AI tools, their data flows, and classification levels.
Define and track KPIs for every AI initiative: workflows automated, hours saved, adoption rates, and user satisfaction.
Develop training sessions, documentation, and self-service resources to accelerate AI adoption among non-technical users.