Security Engineer - Detection & Response

LangChain; New York (NY); On-site; USD 180,000 - 240,000; Full time

Job summary

LangChain is seeking an on‑premise security detection and response engineer to design, build, and scale monitoring across our production platform, cloud infrastructure, and agent workloads. You will translate threat models into telemetry, detections, and durable defenses while partnering with Product Security to reduce risk and drive improvements.

The role emphasizes engineering rather than manual operations, requiring strong Python or Go, Kubernetes experience, and a pragmatic product mindset.

Qualifications

• 5+ years in security engineering, with detection engineering, security operations, or incident response.
• Strong software engineering in Python or Go with production code experience.
• Cloud and Kubernetes detection depth across GCP/AWS, logging, and runtime telemetry.
• Experience building automation and developer-facing systems.

Responsibilities

• Own the detection lifecycle: translate threat models and incidents into telemetry requirements and detections-as-code; validate coverage and reduce false positives.
• Build security monitoring and telemetry across cloud, Kubernetes, and LangSmith/LangGraph control plane; ensure signals are reliable.
• Engineer investigations and threat hunting workflows; turn findings into new detections and improvements.
• Develop internal AI agents and automation to triage alerts and accelerate incident response.
• Lead incident response during on-call rotations; perform postmortems to drive durable changes.
• Collaborate with Product Security to convert threat findings into production monitoring and learnings.

Skills

Python/Go production code

Kubernetes

Threat detection concepts

Incident response

Security telemetry

On-call experience

Tools

Terraform

Helm

Job description

About Us

At LangChain, our mission is to make intelligent agents ubiquitous. We build the foundation for agent engineering in the real world, helping developers move from prototypes to production-ready AI agents that teams can rely on. We began as widely adopted open-source tools and have grown to also offer a platform for building, evaluating, deploying, and operating agents at scale.

With $125M raised at Series B from IVP, Sequoia, Benchmark, CapitalG, and Sapphire Ventures, we’re at a stage where we’re continuing to develop new products, growth is accelerating, and all team members have meaningful impact on what we build and how we work together. LangChain is a place where your contributions can shape how this technology shows up in the real world.

Today, our platform includes LangSmith (Observability, Evaluation, Deployment, Fleet, and Sandboxes), our open source frameworks (LangChain, LangGraph, and Deep Agents), and the newly launched LangSmith Engine for autonomous agent improvement. We have 100M+ monthly open source downloads, 6,000+ active LangSmith customers, and 5 of the Fortune 10 use LangSmith in production (+ 35% of the Fortune 500 overall), including teams at Klarna, Clay, Coinbase, Workday, Lyft, Cloudflare, Harvey, Rippling, Vanta, LinkedIn, Monday.com, Nvidia, and Bridgewater.

About The Team

The Security team ensures that while AI moves at breakneck speed, everyone driving the racecar is wearing a seatbelt. We secure LangChain’s core platform and protect AI agents from emerging threats. We work across the stack so developers can confidently ship from prototype to production without compromising on safety or privacy.

About The Role

You’ll be the hands‑on detection and response engineer responsible for how we see, stop, and learn from threats across LangChain’s production platform, cloud infrastructure, and the services that host and execute agentic workloads. You’ll partner closely with Product Security to turn threat models, vulnerabilities, and incidents into telemetry, detections, and durable defenses. Your primary focus is engineering: building detection, investigation, and response systems that scale the Security team’s impact beyond what manual operations allow. We are looking for engineers who think like builders, not just operators — strong software skills are a must.

This role participates in an incident on‑call rotation, but its core focus is engineering systems that reduce risk, speed up investigations, and make incidents less frequent and less costly.

Location

San Francisco or NYC

What You’ll Do

• Own the detection lifecycle: Translate threat models, incidents, and attacker behavior into telemetry requirements and detections‑as‑code. Validate coverage, measure signal quality, tune false positives, and continuously test whether defenses work.
• Build security monitoring and telemetry: Design the telemetry pipeline end‑to‑end across cloud (GCP/AWS), Kubernetes, and the LangSmith/LangGraph control plane. Instrument services, define the signals that matter, and make security data reliable and useful.
• Engineer investigations and threat hunting: Build tools and workflows for proactive hunting, evidence collection, incident scoping, and containment. Turn investigation findings into new detections and lasting improvements.
• Use agents to scale the team: Build reliable internal AI agents and automation that triage alerts, enrich findings, gather evidence, scope incidents, and accelerate routine security work. Design human‑in‑the‑loop controls and evaluations so automation is safe, observable, and trustworthy.
• Lead incident response and participate in on‑call: Triage, scope, contain, and remediate security incidents, then drive postmortems that produce durable engineering changes.
• Partner with Product Security: Turn product threat models and vulnerability findings into production monitoring, and feed real‑world detection and incident learnings back into secure design.

What You’ll Bring

• 5+ years in security engineering, with meaningful experience in detection engineering, security operations, or incident response — and the software skills to build your way out of repetitive work.
• Strong software engineering in Python or Go (TypeScript a plus). You design maintainable systems and write production code, not just one‑off scripts.
• Cloud and Kubernetes detection depth: Experience with GCP or AWS logging, Kubernetes audit and runtime telemetry, workload identity, and turning raw signals into actionable detections.
• Detection and adversary expertise: The ability to model realistic attacker behavior, hunt across complex systems, test detection coverage, and distinguish meaningful signal from noise.
• Hands‑on incident response: You’ve participated in on‑call, led incidents, and written postmortems that changed how a team operates.
• Experience building reliable automation or developer‑facing systems: You can design APIs and workflows, instrument what you build, evaluate quality, and operate it in production.
• A pragmatic product mindset: You can identify users and requirements, prioritize the highest‑leverage problems, define success, and ship iteratively.

Nice to Have

• Experience building or operating AI agents for security workflows such as alert triage, investigation, evidence collection, or human‑in‑the‑loop response.
• Proficiency using AI tooling to accelerate security investigations and engineering work.
• Understanding of AI threats, adversarial testing, and the security boundaries of LLM and agent workloads.
• Exposure to SOC 2 or ISO 27001 monitoring and evidence automation.
• Experience with infrastructure as code such as Terraform or Helm.
• Experience securing both SaaS and self‑hosted or air‑gapped deployments.

Annual salary range: $180,000- $240,000 USD

Compensation Philosophy

We offer competitive compensation that includes base salary, variable compensation for relevant roles, meaningful equity, benefits, and perks. Actual compensation and offerings will vary based on role, level, and location. Team members in the EU, UK, and APAC receive locally competitive benefits aligned with regional norms and regulations.

Benefits

• Benefits include medical, dental, and vision coverage, flexible vacation, a 401(k) plan, meals on in‑office days in the US and more.