Principal Software Engineer, Huntress

• 15+ years of experience developing complex software products, including significant time as the technical lead on production systems
• Hands-on experience designing, shipping, and operating LLM-based agents in production, covering tool use, context management, structured output, guardrails, and evaluation, along with a clear-eyed understanding of how they fail
• A track record of building evaluation for non-deterministic systems, such as labeled datasets, offline evals, and regression gates, and of measuring quality over time rather than at launch
• A security mindset: experience building systems that handle untrusted input, enforce multi-tenant isolation, and produce an audit trail that holds up under scrutiny
• Experience building systems that make automated decisions with real consequences, and the judgment to know what to automate and what to leave to people
• Curiosity about how security analysts think and work, and a willingness to spend real time learning from them
• Deep backend expertise in distributed systems, queues, and durable workflows, and concurrency, with a track record of designing for throughput and correctness under load
• Strong skills in one or more backend languages and the ability to pick up new ones quickly. Our primary stack is Ruby on Rails, and we expect you to become fluent in it
• Experience with AWS, Azure, or other public cloud environments, and with data stores such as Postgres and Redis
• Experience with AI coding tools, such as Claude Code
• BS or MS in Computer Science or Engineering, or equivalent experience

Desirable

• Huntress is building an Agentic SOC
• When our detection pipeline raises a signal, an LLM-based agent picks it up and investigates it end-to-end
• It gathers telemetry across our products, reconstructs what happened, and makes a well-documented determination about whether the activity is malicious
• Over time, it will take on more of the work itself, growing from resolving routine cases to acting fast when it finds an attack and handing analysts cases with the evidence already assembled
• We’re hiring a Principal Software Engineer to head this effort
• This system is meant to augment our analysts, not replace them
• It takes the high-volume, repetitive work off their plates so they can focus on complex cases and hands-on keyboard intrusions where human expertise matters most
• It also reduces toil in the rest of their day by using LLMs to pre-process the output of the tools analysts use constantly, so they start from a clear picture instead of raw telemetry
• This isn’t a chatbot bolted onto a dashboard
• The system investigates a large volume of signals a day across thousands of customer organizations
• Many signals are benign, but some are live intrusions where minutes matter
• The telemetry the system reads comes from environments in which attackers are actively operating
• Because the system makes real decisions, like closing an investigation or isolating a host, it has to be right, it has to show its work, and it has to know when to hand off to a person
• As the technical lead, you’ll own the system’s architecture and direction
• That means deciding how an investigation is structured, where deterministic code ends and model reasoning begins, what the agent can and can’t touch, how we know it’s working, and which decisions it makes on its own as it proves itself
• You’ll work closely with SOC analysts, detection engineers, product, and other engineering teams
• You’ll go deep in the code and help the engineers around you grow
• Your work will directly shape how Huntress scales protection for the 99%
• We make full use of AI coding tools to enable you to accelerate your development
• We don’t cap token usage
• We expect you to use AI and all tools responsibly
• Own the architecture of agentic investigation. You help define how signals move from detection into investigation, how investigation state is managed, how tools are designed and exposed to agents, and what a finished investigation contains: the verdict, the timeline, the scope, and the evidence behind every claim. When the team is stuck between options, you make the call, and the foundations you set are what others build on for years
• Build agents that investigate like a strong analyst. You work alongside our SOC and product researchers to learn how experienced analysts actually triage and investigate, then turn that into agent behavior: which questions to ask, which evidence to gather, when to dig deeper, and when to stop and hand off to a human
• Take toil off analysts’ plates. Beyond full investigations, you build LLM-powered pre-processing for the tools and data sources analysts rely on every day. It summarizes, correlates, and highlights what matters, so analysts spend their time on judgment instead of assembly
• Bring a security mindset to the agent itself. The agent reads attacker-influenced data, runs across thousands of customer tenants, and can take action in customer environments. You design as if someone is trying to manipulate it, because someone will. Trust boundaries, tenant isolation, and auditability are part of the architecture from the start
• Treat evaluation as a core part of the product. You define how we measure whether an investigation is correct, well-reasoned, and well-documented, and you make sure no prompt, model, or tool changes without evidence that it helps
• Decide with data what the system does on its own. Based on measured performance, you decide where it acts autonomously, where a person reviews its work, and how that changes over time. You also recognize when a problem doesn’t need an agent at all
• Build for production, not for demos. You design for reliability, latency, and cost at scale. The system keeps working when models are slow, wrong, unavailable, or quietly changed underneath you, and anyone can trace exactly why an investigation reached its conclusion or why an action was taken
• Augment analysts, don’t replace them. You design the handoff between agent and analyst so that when a case reaches a person, the agent’s work makes them faster and better informed. You consider how analysts’ work changes as agents take on more of it, and how we explain agent decisions to partners and customers in a way they can trust
• Prototype your way through hard problems. When the team hits something genuinely uncertain, you dig in first: derisk it, prove out the approach, then hand it off clearly
• Be the engineering face of the Agentic SOC. In conversations with SOC leadership, other engineering teams, product, and executives, you represent the team’s technical perspective clearly and credibly. You drive alignment on key decisions, carry context in both directions, and protect the team from unclear scope
• Balance technical rigor with pragmatism. You push back when a shortcut creates real risk, and you also push back on over-engineering when the goal is discovery. You have a bias for action and frequent feedback from analysts and customers, and you can explain your tradeoffs to engineers and non-engineers alike
• Raise the floor and the ceiling. Your technical leadership is measured by how the whole team performs, not just by what you personally ship. That shows up in thoughtful code review, pairing on problems others are stuck on, and creating leverage through better patterns, tooling, and shared understanding. You partner with the engineering manager on team health, give direct feedback, and model the judgment and accountability you want the team to have