Backslash Security

Description Applied Data Scientist — Intent Drift Detection Backslash Security · Realtime AI-agent protection About Backslash We are builders who want to secure the next generation of software development from the inside out. Software development has entered a new era defined by vibe-coding, MCP servers, and AI agents. While these tools allow developers to build faster than ever, they also introduce a completely new frontier of security challenges that exist directly on the engineer's machine. Backslash is building the security layer for this new reality. We provide the essential guardrails and visibility needed to secure AI-driven workflows. By actively protecting developer computers and monitoring IDE-based AI interactions, we ensure the future of coding is as secure as it is fast. The Role AI coding agents run with enormous privilege on developer machines. When untrusted content steers one off its task, classical security sees only the final action — never that the agent's intent drifted. Detecting that drift, in realtime, on-device, is an open problem. No one has solved it. You will. You will own intent-drift detection end-to-end — from the data to the model: • Build the Dataset: Design and generate the data that defines what "drift" looks like, and co-design the pipeline that creates it. • Train Small, Ship Local: Fine-tune, distill, and shrink the models that detect drift in realtime — small enough to run fully on-device, no cloud. • Shape the Architecture: Decide what's a model, what's a rule, and what's a gate. The detector's design is your call. • Measure What Matters: Build the evaluation harness — realtime detection at very low false-positive rates on a developer's machine is the product. You own intent-drift analysis as a problem, not a ticket. Requirements • Applied Data Science End-to-End: 3–5 years turning ambiguous problems into working models — problem framing, data collection and labeling strategy, feature/representation design, training, and evaluation. You've owned a dataset and the model that consumed it. • Small-Model Fluency: Comfortable fine-tuning small open models locally — DeBERTa-class encoders, ≤8B decoders, LoRA, quantization, single-GPU workflows. • Applied-Research Mindset: You approach an open research problem with passion and a practical, ship-it attitude. • Independence: You want an impactful, strategic problem in LLM security — not a ticket queue. • Startup DNA: Can-do, fast, a true partner. Non-negotiable. Local-first by design. Python, PyTorch, HuggingFace, ≤8B models. Bonus Points For • Security Background: Prompt injection, MITRE ATLAS, agent security — or the hunger to learn it fast. • Adversarial ML: Experience with LLM evaluation, red-teaming, or building adversarial datasets. • Endpoint Software: Familiarity with software that runs locally on developer machines with a low resource footprint.

Description About Backslash Backslash is a Series A startup on a mission to make AI-assisted development safe by default. As AI coding agents and modern dev environments like Cursor and Claude Code reshape how software is written, we are building the security layer that understands where AI introduces new, hidden risk and protects against it. We are a focused team with a simple goal: let engineering teams adopt AI at full speed with maximum visibility and safety. The role You will lead Backslash's security research - discovering how AI coding agents create new attack surfaces, and turning those findings into product direction and market narrative. This is a hands-on role where you drive original research while managing broader research activities across the company. You will be a trusted technical voice across product, architecture, and marketing. You report to the CTO. What you will do • Lead security research on AI coding agent attack surfaces, emerging threats, and novel vulnerability classes - from MCP security to prompt injection in dev environments • Publish original research - blog posts, conference talks, CVEs, technical deep-dives - that establishes Backslash as a thought leader in AI security • Feed research findings into product - identify security weaknesses, inform architecture decisions, and shape the roadmap • Track the AI security landscape - tools, protocols, attack vectors, academic research - and translate what matters into what we build • Be a go-to technical resource for marketing, sales, and product - translating research into content, customer conversations, and competitive positioning What success looks like in your first 6 months • Published 2-3 pieces of original research that the AI security community is talking about • Identified novel attack classes specific to AI coding agents that shaped our product roadmap • Became a trusted technical voice in customer conversations and industry events • Built a clear research agenda for the following 12 months What you bring • Established security researcher - you've done this work long enough to have a track record and a point of view • Prior experience in a similar role - security research lead, principal researcher, or equivalent • Experience with AI/LLM security - prompt injection, agent-based attacks, model supply chain risks • Understanding of endpoint security, agent architectures, and local-machine threat models • Offensive mindset - you instinctively think about how to break things, not just how to describe them • Published research track record (blogs, CVEs, conference talks) • Experience translating research into product features and architecture decisions • Hands-on, pragmatic, and biased to action When applying, please include links to published research, blog posts, or conference talks.

Description About Backslash We are builders who want to secure the next generation of software development from the inside out. Software development has entered a new era defined by Vibe-coding, MCP servers, and AI Agents. While these tools allow developers to build faster than ever, they also introduce a completely new frontier of security challenges that exist directly on the engineer's machine. Backslash is building the security layer for this new reality. We provide the essential guardrails and visibility needed to secure AI-driven workflows. By actively protecting developer computers and monitoring IDE-based AI interactions, we ensure the future of coding is as secure as it is fast. The Role As an Engineer, you will be responsible for the infrastructure that connects our local protection agents to our high-scale cloud backend. • Architect Distributed Systems: Design and evolve a robust microservices architecture capable of handling high-throughput telemetry and security events from thousands of distributed developer machines. • Master Endpoint Deployment: Own the delivery and lifecycle of our protection agent, ensuring it deploys seamlessly to engineer laptops and runs with a zero-friction resource footprint. • Scale Data Infrastructure: Build the backend pipelines and storage solutions that ingest, process, and provide visibility into real-time security data from IDEs and local AI tools. • Deliver Full-Stack Features: Take end-to-end ownership of features, contributing to the user interface to ensure backend data and endpoint health are presented clearly to our users. • Drive Technical Excellence: Set the standard for stability through automated quality gates and a commitment to building low-latency, resilient software that developers can trust on their machines. Requirements We’re looking for a backend specialist who thinks in systems and data flow but can navigate the full stack when the feature requires it. • Engineering Depth: 5+ years of software engineering experience, with a track record of shipping complex backend systems or distributed architectures. • Micro-services Mastery: Hands-on experience designing and maintaining microservices in production, including service discovery, inter-service communication, and high-scale data ingestion. • Backend Expertise: Highly proficient in server-side development using modern ecosystems (like NestJS, Adonis etc.) and a strong command of TypeScript/Node.js. • Full-Stack Capability: Practical experience with modern frontend frameworks (like React or Vue). You are comfortable building UI components to visualize the telemetry and insights of backend processes. • Cloud Native: Strong experience with containerization (Docker, Kubernetes) and major cloud platforms (AWS, GCP, or Azure). • Startup DNA: You thrive on ownership. You want to solve problems, not just execute tasks. Bonus points for • Endpoint & Systems: Familiarity with building software that runs locally on macOS, Linux, or Windows (background agents, daemons, or system services). • Cybersecurity Interest: Experience in EDR/XDR, endpoint protection, or a deep interest in securing developer workflows. • Data Scale: Experience designing and implementing complex algorithms or high-performance data pipelines.

Description About Backslash Security Backslash Security secures the new way software gets built. AI coding agents such as Cursor, Claude Code, Codex, GitHub Copilot, and OpenClaw now write and run code on developer workstations, connect to MCP servers, and follow prompt rules and skills that nobody reviews. Backslash gives security teams visibility and control over this agentic layer. That covers agents, MCP servers, rules, models, and the endpoints they run on, so organizations can adopt "vibe coding" safely without slowing developers down. We are a fast-growing startup of about 30 people. Every person here has a large impact on the product and the company. The Role We're hiring a Senior Product Manager / Director of Product who reports directly to the VP of Product. You will own major parts of the Backslash platform from discovery through launch and adoption. You'll define what we build and why, work closely with engineering to ship it, and work with customers, sales, and customer success to make sure it wins in the field. This is a senior, hands-on role in a category that is still taking shape. The job is less about managing a backlog and more about deciding what the right answer is when no one has solved the problem before. What You'll Do • Own product areas end to end. Set strategy, write specs, prioritize, launch, and track adoption for key parts of the platform, such as agent and MCP discovery, risk detection, policy and guardrails, and endpoint coverage. • Shape the roadmap with the VP of Product. Turn market signals, customer feedback, and competitive dynamics into a clear, prioritized plan. • Be deep in the market. Stay ahead of how AI coding agents, MCP, and developer tooling are evolving, and turn that into product bets and positioning. • Work with customers directly. Run discovery interviews, join POVs and strategic customer calls, and turn what you learn into product decisions that close deals and drive renewals. • Partner with engineering to ship high-quality product quickly. Write clear PRDs and user stories, define acceptance criteria and success metrics, and make trade-offs with the engineering leads. • Enable go-to-market. Work with sales, sales engineering, customer success, and marketing on launches, messaging, demos, and competitive positioning. • Make decisions with data. Define and track product KPIs, including adoption, detection quality, time-to-value, and POV conversion, and use them to steer. • At the Director level: help build the product function, raise the bar on product process, and mentor or eventually manage other PMs. Requirements Requirements • 7+ years of product management experience (5+ for Senior PM), with a significant part of it in cybersecurity or deeply technical B2B / developer products. • Proven track record of launching and scaling software products across the full lifecycle, from 0→1 through growth, ideally in a startup or high-growth environment. • Strong technical depth. You're comfortable talking with engineers about architecture and with security practitioners about threats and controls. Hands-on familiarity with developer workflows (IDEs, CLIs, CI/CD, SCM) is expected. • Strong analytical skills and a habit of data-driven decision-making. • Excellent communication and executive presence. You can write a crisp spec, present the roadmap to a CISO, and align a cross-functional team around a decision. • Customer-facing experience in enterprise sales cycles, such as discovery, POVs/POCs, and working with champions and security buyers. • Experience with modern product practices such as Agile/Scrum and continuous discovery, and with standard PM tools (Jira, Notion, analytics platforms). • Comfort with ambiguity, a bias to action, and a sense of ownership that goes well beyond your job title. Nice to Have • Experience in endpoint security, or supply-chain security (SAST, SCA, EDR, ASPM, secrets, etc.). • Hands-on experience with AI coding agents, LLMs, and MCP. You use these tools yourself and have opinions about where they break. • Background as an engineer, security researcher, or sales engineer before moving into product. • Experience building or leading a product team, for Director-level candidates. • Thought leadership presence, such as talks, writing, or podcasts in security or AI. Why Join • Define a brand-new security category at the moment it's forming. • Real ownership and direct impact on the product, the customers, and the company's trajectory. • Work closely with the VP of Product, the founders, and a strong engineering team. • Competitive compensation and meaningful equity.