Applied AI Engineer

About Us Simbian® is building Agentic AI platform for cybersecurity. Founded by repeat successful security founders, we have gathered an excellent cohort of employees, partners, and customers. Our mission is to solve security using AI and our core values are excellence, replication, and intellectual honesty. Our promise is to make Simbian the best workplace of your career and we believe a small group of thoughtful passionate people can make all the positive difference in the world. To fuel our fast growth, we are seeking an exceptional candidate who shares our core values of excellence (being the world's best at our craft), replication (share your best ideas with others), and intellectual honesty (tell the truth even if it's bitter). Our AI Agents automate security operations and provide our customers 10x leverage. Our customers include some of the world's largest companies. Our initial use cases include: SOC alert triage and investigation Prioritization and classification of vulnerabilities AI based threat hunting Job Description About Simbian Simbian is building an Agentic AI platform for cybersecurity. Our AI agents automate security operations and provide customers with 10x leverage across critical security workflows. Our initial use cases include: • AI-based SOC alert triage and investigation • AI-based Threat Hunting • AI-based Penetration Testing Founded by repeat successful security founders, Simbian brings together a strong team of engineers, security experts, and operators working on some of the hardest problems at the intersection of cybersecurity and AI. Our core values are excellence, replication, and intellectual honesty. We believe in building exceptional technology, sharing what we learn, and being honest about what works—and what doesn't. The Role We are looking for an Applied AI Engineer to help build the systems that make our AI agents powerful, reliable, and useful in real-world cybersecurity environments. This role sits at the intersection of backend engineering, distributed systems, and applied AI. You will build the backend infrastructure that powers our agents while also working directly on agent behavior—improving how agents reason, use tools, retrieve context, handle failures, and complete complex tasks. The goal isn't simply to build models or backend services in isolation. It's to turn AI capabilities into dependable production systems that solve real customer problems. You'll work closely with research, engineering, product, and security teams to take ideas from experimentation to production and measure whether they improve agent performance. Requirements Applied AI & Agent Systems • Design and iterate on AI agent behaviors across real-world cybersecurity and software engineering workflows. • Build multi-step agent workflows with tool calling, branching logic, retries, validation, and human-in-the-loop controls. • Develop tool schemas, execution strategies, context construction, memory, and retrieval mechanisms that improve agent performance. • Experiment with prompting, model-facing strategies, tool-use patterns, and context engineering. • Analyze agent failures and systematically turn failure modes into product and engineering improvements. • Build guardrails, policy layers, and safe-execution mechanisms for agents operating in security-sensitive environments. • Help define what "good" looks like for an agent completing complex tasks end-to end. Evaluation & Agent Performance • Design and run evaluations to measure agent quality, reliability, regressions, and edge cases. • Build evaluation pipelines, test harnesses, scoring frameworks, and golden datasets. • Create feedback loops that bring real-world task data and production failures back into evaluation and development. • Analyze production traces and agent behavior to identify opportunities for improving solve rate, usefulness, and reliability. • Work with research and engineering teams to translate experimental improvements into measurable production gains. Backend & Distributed Systems • Design and build scalable backend services that power AI agents and cybersecurity workflows. • Build high-scale, multi-tenant systems that securely support multiple customer environments. • Work with microservices, asynchronous execution, event-driven architectures, and distributed systems. • Build ingestion, indexing, retrieval, and agent-memory layers for large volumes of security data. • Design reliable execution systems with strong observability, traceability, monitoring, and data-quality guarantees. • Build and maintain integrations with enterprise security platforms such as SIEM, SOAR, EDR, and NDR systems. • Own features end-to-end—from architecture and implementation through deployment, monitoring, debugging, and iteration in production. Product & Cross-functional Collaboration • Work closely with product, research, infrastructure, and security teams to turn ambiguous problems into working systems. • Partner with customer-facing teams to understand real-world failures and improve the product based on user needs. • Help shape the interfaces and workflows through which users interact with AI agents. • Contribute to architectural decisions and technical direction as the platform evolves • Have 5–8 years of software engineering experience, with strong backend development experience. • Have experience building and shipping ML/LLM-powered products or AI-enabled features, or have strong hands-on experience applying LLMs to real engineering problems. • Are highly proficient in Python and comfortable working with modern AI/ML tooling. • Have strong fundamentals in distributed systems, backend architecture, APIs, microservices, and asynchronous systems. • Have experience with LLMs, prompt engineering, RAG, embeddings, model evaluation, or agentic systems. • Think beyond model metrics and engineering elegance—you care about whether the system actually works for users. • Enjoy debugging messy, real-world failures and turning them into systematic improvements. • Are comfortable working in ambiguous environments and taking ownership from problem definition → implementation → production. • Have a strong understanding of software engineering fundamentals and write clean, maintainable, well-tested code. • Enjoy reading technical papers, RFCs, experimenting with new technologies, and learning quickly. Must Have • 4–7 years of professional software engineering experience. • Strong backend development experience, preferably with Python, Go, or Node.js. • Strong understanding of distributed systems fundamentals. • Experience with microservices, APIs, asynchronous execution, and event-driven systems. • Hands-on experience with LLMs / Generative AI / Applied AI. • Experience with at least some of: o Prompt engineering o RAG o Embeddings / vector databases o LLM evaluation o Tool calling / function calling o Agent frameworks • Experience building and deploying production software. • Strong problem-solving and debugging skills. • Ownership mindset and ability to take a problem from zero to shipped. Bonus / Great to Have • Experience building AI agents or tool-using LLM systems. • Experience with LangGraph, LangChain, or similar agent frameworks. • Experience with model evaluation, fine-tuning, or code-generation models. • Experience building developer tooling or AI coding systems. • Experience with cybersecurity products, particularly SIEM, SOAR, EDR, NDR, or security data pipelines. • Experience with AWS/GCP/Azure, Docker, Kubernetes, and CI/CD. • Experience building evaluation frameworks, benchmark datasets, or automated testing systems for AI agents. • Experience with agent observability, tracing, and production LLM monitoring. • Strong academic background in Computer Science or a related field; graduates from IITs or other top-tier engineering institutions preferred. Benefits • Build an AI-first cybersecurity platform from the ground up. • Work at the intersection of AI, cybersecurity, and distributed systems. • Solve problems where there isn't always an obvious playbook. • Work directly with founders, researchers, security experts, and engineering leaders. • Own meaningful problems end-to-end and see your work go directly into production. • Be part of an early team where your technical decisions and ideas can have outsized impact. • Ship fast, learn fast, and build systems that matter.