人工智能工程师 – 自主 AI 与云发现
AI Engineer – Agentic AI & Cloud Discovery
职位地点：印度，远程优先
工作类型：全职
入职时间：2026年11月
经验要求：4年以上
语言要求：英语流利
行业：网络安全 / 企业SaaS / AI安全
关于该职位
Pragmatike正在为一家全球企业网络安全公司招聘，该公司正在打造新一代产品，用于保护AI代理、LLM驱动的应用程序以及它们访问的数据。
工程团队正在印度迅速扩张，目前有两个AI工程师职位，专注于将AI和机器学习能力转化为可靠、生产级的安全产品。
我们寻找的工程师既能使用Go构建生产服务，也能使用Python开发LLM/ML流水线，并能快速从实验过渡到稳定生产的系统。
你将加入以下两个工作流之一：
- 代理AI取证：利用LLM推理、RAG、结构化提取和严格评估，将代理痕迹、提示、工具调用和安全事件转化为结构化、可解释的发现，供安全分析师使用。
- 云资源发现：对云资源和工作负载进行分类，以识别AI代理、模型端点和AI驱动的应用程序，同时通过大规模LLM/ML分类推断其用途和安全风险。
两个工作流共享相同的基础：Go用于生产服务，Python用于实验和数据流水线，LLM API，严格评估，以及云原生部署。
你将负责
- 设计并构建LLM驱动的分析和分类流水线，然后将其生产化为Go服务。
- 使用Python进行原型设计，包括提示策略、RAG、结构化提取和ML分类器，并交付符合定义准确率目标的解决方案。
- 定义真实数据集、评估指标和回归测试套件，持续测量和提升模型质量。
- 监控生产中的模型质量和漂移，并建立流程以识别和解决退化问题。
- 与安全研究人员合作，将攻击模式和风险信号转化为检测和摘要逻辑。
- 将AI驱动的功能与事件、存储和UI层集成，向安全团队展示可操作的结果。
- 使用AI辅助开发流程加速实现、测试、调试和实验。
我们寻找的人才
- 4年以上软件工程经验，其中至少2年有LLM或ML支持的功能开发经验
查看英文原文
Location: India, Remote-First
Employment: Full-Time
Start Date: November 2026
Experience: 4+ years
Language: Fluent English required
Industry: Cybersecurity / Enterprise SaaS / AI Security
ABOUT THE OPPORTUNITY
Pragmatike is recruiting on behalf of a global enterprise cybersecurity company building a new generation of products to secure AI agents, LLM-powered applications, and the data they access.
The engineering organization is scaling rapidly in India, with two AI Engineer openings focused on turning AI and machine learning capabilities into reliable, production-grade security products.
We’re looking for engineers who are equally comfortable building production services in Go and developing LLM/ML pipelines in Python, with the ability to move quickly from experimentation to hardened production systems.
You’ll join one of two workstreams:
- Agentic AI Forensics: Turn agent traces, prompts, tool calls, and security events into structured, explainable findings for security analysts using LLM reasoning, RAG, structured extraction, and rigorous evaluation.
- Cloud Discovery: Classify cloud resources and workloads to identify AI agents, model endpoints, and AI-enabled applications, while inferring their purpose and security risk using LLM/ML classification at scale.
Both workstreams share the same foundations: Go for production services, Python for experimentation and data pipelines, LLM APIs, rigorous evaluation, and cloud-native deployment.
WHAT YOU’LL DO
- Design and build LLM-powered analysis and classification pipelines, then productionize them as Go services.
- Prototype approaches in Python, including prompting strategies, RAG, structured extraction, and ML classifiers, and ship solutions that meet defined accuracy targets.
- Define ground-truth datasets, evaluation metrics, and regression suites to continuously measure and improve model quality.
- Monitor model quality and drift in production and build processes to identify and address degradation.
- Collaborate with security researchers to translate attack patterns and risk signals into detection and summarization logic.
- Integrate AI-powered capabilities with event, storage, and UI layers to surface actionable results to security teams.
- Use AI-assisted development workflows to accelerate implementation, testing, debugging, and experimentation.
WHAT WE’RE LOOKING FOR
- 4+ years of software engineering experience, including 2+ years shipping LLM- or ML-backed features to production.
- Strong Go skills for production backend services and strong Python skills for experimentation and data pipelines.
- Hands-on experience with LLM APIs, prompt engineering, structured outputs, and RAG.
- Experience evaluating LLM/ML systems through offline evaluations, human review, regression suites, or similar approaches.
- Understanding of AI agent architectures, including tool calling, MCP or similar protocols, multi-step planning, and common failure modes.
- Experience with cloud-native deployment using Docker, Kubernetes, and AWS, GCP, or Azure.
- Fluent English with strong written and verbal communication skills.
- Comfortable using modern AI coding assistants such as Claude Code, Cursor, GitHub Copilot, Codex, or similar. This is a must-have.
- Strong ownership and the ability to work independently in a remote-first, distributed environment.
NICE TO HAVE
- Background in security analytics, SIEM/SOAR, or digital forensics.
- Practical knowledge of major cloud provider APIs, IAM models, and resource inventory.
- Experience with vector databases, embedding pipelines, or model fine-tuning for classification or extraction.
- Familiarity with tracing AI applications and OpenTelemetry-style observability.
- Previous experience in cybersecurity, security tooling, or trust & safety.
- Experience introducing AI-assisted or agentic development workflows across engineering teams.
AI-FIRST ENGINEERING
AI is a core part of the engineering workflow on this team.
During the interview process, you'll be asked about how you use AI in real-world software development, including the tools you use, how you validate their output, and where AI has changed the way you work.
We're looking for engineers who use AI as a force multiplier for quality, productivity, and problem-solving, not simply as an autocomplete tool.
WHY JOIN
- Work on a greenfield product at the intersection of cybersecurity and agentic AI.
- Turn cutting-edge LLM/ML approaches into production systems protecting enterprise customers.
- Work across both AI experimentation and production engineering, from Python prototypes to Go services.
- Take ownership of a key workstream and influence architecture from an early stage.
- Collaborate with a highly technical, distributed team where AI is a core part of the development process.
Pragmatike is committed to a fair, transparent, and inclusive recruitment process. We do not discriminate based on age, disability, gender, gender identity or expression, marital or civil partner status, pregnancy or maternity, race, religion or belief, sex, or sexual orientation.
In accordance with GDPR, your personal data will be processed lawfully, fairly, and securely and used solely for recruitment purposes, including sharing it with our client(s) for employment consideration.