Build the agent runtime and the LLM application layer that powers our company Agents - the ai-gateway that routes across Anthropic, OpenAI, and our own served models, plus tools, MCP, deep-research orchestration, and the App Builder codegen loop. You will turn frontier and owned models into product features people actually depend on.

our company's product is built around an AI agent that security analysts and detection engineers work with directly. It investigates coverage questions against live enterprise security data, authors and tests detection logic, and tunes noisy alerting.
That agent is already in production with enterprise design partners. Now we need to make it dependable and scalable enough for GA.
You will own that evolution: the agent architecture, its evaluation and quality system, and the production engineering around it. This is a hands-on senior IC role with real architectural authority - you set the technical direction and you write the code.
The agent operates inside customer security environments, where a wrong action can become a customer incident. Correctness, isolation, observability, and evaluation are not polish. They are the product.
What you'll be doing
Agent architecture: Design the evolution from today's production single-agent system to a multi-agent one: orchestration, task decomposition, runtime and framework choices, and a migration path that does not break what design partners already rely on.
Agent capability: Own the prompts, context, skills, and tool design that make the agent genuinely good at detection engineering across multiple security platforms, not just plausible-sounding.
Evaluation platform: Build the harnesses, judges, and golden datasets that turn "the agent feels better" into a number, plus the CI gates that keep regressions from shipping.
Reliability and safety: Keep long-running agentic sessions healthy in production, and build the isolation and guardrails required of an agent working inside enterprise security environments.
Production debugging: Work real failures from production traces, and turn each one into an eval case that can never regress silently.
Technical direction: Make the calls on architecture, sequencing, and quality bar and be accountable for the outcome, including raising how AI-natively the whole team builds.
Cross-team partnership: Partner with product and customer-facing teams on what the agent should do, and with platform teams on the data and integrations it depends on.

As a Senior Applied AI Engineer, you will lead the bridge between cutting-edge AI capabilities and production-grade software. You will design, build, and optimize the intelligent systems, agentic workflows, and LLM-driven architectures that power our companys conversational products.
Also, you will combine software engineering rigour with state-of-the-art Generative AI techniques - optimizing for conversational quality metrics, latency, and system reliability in high-scale production environments, serving millions of users. We are looking for an engineer who is hungry for AI innovation, eager to pioneer new generative capabilities, and passionate about shipping impactful AI solutions.
In this role, you will:
Design & Scale AI Systems: Architect and deploy high-performance LLM orchestration systems, agentic workflows, retrieval-augmented generation (RAG) pipelines, and AI microservices.
Bridge AI Research & Production: Transform frontier LLM research, foundation models, and generative techniques into robust, production-ready features with high availability and low latency.
LLM Evaluation & Guardrails: Design and implement automated LLM evaluation (evals) frameworks, benchmark suites, and guardrail policies to continuously measure accuracy, reduce hallucinations, and ensure safety across product flows.
Optimize Performance & Cost: Lead latency, throughput, and token-cost optimization strategies across commercial APIs and open-source models.
Set AI Engineering Standards: Elevate software craftsmanship across the team through architectural reviews, code quality, and LLMOps best practices, utilizing the latest AI tools.
Drive Product Innovation: Collaborate closely with product and engineering teams to translate complex human resource and conversational challenges into intelligent software solutions.

Were looking for a highly motivated AI Developer to help design, build, and deploy intelligent agentic systems across our product ecosystem. In this role, you'll work at the intersection of machine learning, backend systems, and modern frontend technologies to deliver AI-first features that feel magical to users.

This is a hands-on, cross-functional role ideal for engineers who love building full-fledged features-from data pipelines and LLM orchestration to intuitive UI experiences-with a strong product mindset.

Responsibilities:
AI Agent Design & Integration
Design and implement autonomous or semi-autonomous agents using LLMs (e.g., OpenAI, Anthropic, open-source models).
Work with prompt engineering, RAG pipelines, and tool/plugin integrations to enable agents to interact with internal and external systems.
Build scalable agent runtimes and orchestration layers (e.g., LangChain, Semantic Kernel, ReAct-based agents).
Fullstack Product Development
Own full-stack features end-to-end: from backend APIs and data models to React-based frontend interfaces.
Integrate AI/agent capabilities into customer-facing products with clean UX and measurable performance.
Collaborate closely with design, product, and data teams to bring ideas from concept to production.
Systems & Infrastructure
Build and maintain backend services and pipelines that support AI agents, including vector search, embeddings, function calling, and observability.
Optimize inference flows for performance and cost, potentially using streaming, caching, or local model inference.
Ensure systems are secure, reliable, and compliant with InfoSec standards.
Experimentation & Continuous Improvement
Rapidly prototype and iterate on new AI capabilities and user experiences.
Analyze performance and usage metrics to drive product and model improvements.
Stay up to date with the evolving AI toolchain and emerging agent architectures.

our company already runs agents in production. Our WAF Copilot takes a freshly disclosed CVE and turns it into a validated, provider-specific WAF rule - a state-driven agent graph that researches the vulnerability, maps the attack surface, composes the rule, then attacks its own output with an independent bypass judge and a false-positive prober before a human is ever offered a deploy. When a weakness survives, the system downgrades its own recommendation and records what it could not prove.
That last part is the thesis of this role.
An agent that touches production security must prove it works and declare what it couldn't prove. The security industry is about to be flooded with agentic claims nobody can verify. We intend to be the company that made verification legible - and that starts with holding our own agents to a standard we're willing to publish.
We're looking for an AI Tech Lead to own that standard across three surfaces:
The platform - Today each agent flow is close to a bespoke implementation. You'll turn our hard-won patterns into shared components, conventions, and infrastructure so the next agent is a week of work rather than a quarter - with evaluation, observability, and cost control built in rather than bolted on.
Enablement - our company's advantage compounds only if the whole company is AI-fluent, not just R&D. You'll raise that fluency everywhere - engineering, research, product, GTM - through tooling, patterns, and teaching.
The voice - You'll publish the methodology: how we benchmark agentic security output, how we model residual risk, what we learned failing. This is a category-defining position and we want it argued in public.
This is a hands-on lead role with no direct reports. Your authority comes from the quality of what you build and how clearly you explain it.
What You'll Do
Define and build our company's agent framework - shared components, orchestration patterns, tool interfaces, and conventions that make "how do I build an agent here" a five-minute answer.
Make evaluation a gate, not an afterthought: trajectory testing, golden datasets, offline replay, and per-dimension scoring that runs in CI. Land the release benchmark so promote / hold / rollback is a number, not a vibe.
Own agent observability end to end - the execution graph, tool invocations, intermediate reasoning, latency per step, and quality drift - including the external Temporal-orchestrated flows that are hardest to introspect today.
Own the economics: provider abstraction, model routing by task complexity, small-model substitution where it holds, cost attribution per flow. Thousands of CVEs through a labeling agent is a budget line, not a detail.
Drive latency and determinism in our production agent flows - tighter loops, early stopping, deterministic state machines over prose-in-prompt orchestration.
Raise the company's AI fluency. Build the internal tooling, skills, and playbooks that let every team - not just R&D - work AI-natively, and teach the judgment for when not to.
Partner with security research, product, and engineering leadership so agent capability and product roadmap actually converge.

We're looking for an AI-native engineer to build the autonomous agents that power our SalesOS. You'll work directly under the engineering head and the founders, and you'll be the one bringing the agents to life. The architecture gets set above you; the agents get built by you. Do this well and you grow fast.
We're now bringing in the engineer who will turn agent designs into shipped, reliable systems - the discovery prompts, the objection-handling logic, the orchestration that decides what the coach says and when.
This role sits close to the heart of the product. The person who gets this right will write code that real reps lean on during real deals.
A word of honesty:
This is an early-team role at a fast-moving company, which means it is hands-on and unglamorous in the way that matters. You will write the agent code, not just diagram it. You will build the eval harness yourself. You will chase down why a coaching response was wrong at 9pm because a customer demo is tomorrow. You will work from a product requirement, figure out the right agent design, and live with the calls you make. The senior team sets the architecture, but inside it you own the implementation end to end - and "it works on my machine" is not the bar. If you want a research seat where you read papers and prototype in notebooks, this is the wrong role. If you want to ship autonomous agents into production and watch them earn their keep on live sales calls, read on.
What you'll do:
Build and iterate the agents themselves - from design to production: coaching reps, analyzing deals, surfacing insight in real time.
Build tool-use and integrations that let agents reach CRMs, transcripts, calendars, and internal data (Gong, Fireflies, Stripe, Apollo, Resend).
Build prompt pipelines for structured outputs, classification, summarization, and coaching feedback - and the eval harnesses that prove they're good.
Write orchestration code that manages agent state, retries, fallbacks, and human-in-the-loop checkpoints - including the failure paths most people skip.
Own the database operations, FastAPI endpoints, and background workers that the agent workflows run on.

We are at the forefront of the AI revolution, delivering brand new accelerated compute platforms for global impact. Our Network Architecture group is seeking a talented and motivated Sr. Software Engineer to build the agentic workflows that our architects use in their daily work. The software at the center of this role is our hardware network simulation environment - you will design multi-step agent workflows over it, engineer the context that grounds them in our own specifications and source code, and optimize their runtime performance. If you are passionate about building the practical infrastructure that brings intelligent agents to life, we want to hear from you.


What you'll be doing:
Build agentic workflows - loops, graphs, and multi-step pipelines - that carry real hardware network simulation and analysis work end to end.
Engineer the context these workflows run on, turning our simulation models, specifications, design documents, and source code into context that makes agents accurate in our domain.
Work closely with network architects to understand their workflows and translate them into agent workflows they use daily.
Optimize the runtime performance of our simulation tooling on these platforms, including execution time, compute cost, and end-to-end latency.
Define evaluation and regression testing for agent workflows, so that changes to a prompt, a graph, or a context source are measurable.
Build observability across agent runs: what the agent did, where it failed, and why.
Champion guidelines for secure and reliable agent workflows, including data handling, access control, and interaction boundaries.
Serve as a key technical resource for solving sophisticated integration issues between agents and internal tooling.

We're looking for a hands-on Agentic AI Engineer to build practical, high-impact AI solutions for our Product Support organization.
This is not a research role. You'll design and ship real AI systems that improve support workflows and processes - building custom solutions where off-the-shelf tools fall short. The role also requires close collaboration across teams: aligning with different stakeholders' needs and priorities, and building strong, ongoing partnerships across the organization.
Responsibilities:
Partner directly with business teams to identify automation and optimization opportunities
Design and implement agent-based AI workflows to automate internal processes end-to-end
Design and build LLM-powered tools (agents, workflows, copilots) using frameworks like LangGraph / LangChain
Develop RAG pipelines, integrate multiple data sources, and build intelligent automation flows
Deep-dive into company data - validate quality, uncover gaps, and ensure AI solutions are built on solid foundations
Take solutions from idea → prototype → production
Governance, Reliability & Security
Ensure AI workflows comply with security, privacy, and compliance requirements
Implement guardrails, approvals, logging, and human-in-the-loop mechanisms where needed
Monitor AI performance, errors, hallucinations, and drift
Collaboration & Enablement:
Partner with business owners to identify automation opportunities
Translate business requirements into AI-driven solutions
Document AI flows, decision logic, and operational runbooks
Educate internal teams on AI capabilities and limitations.

We are looking for an AI Engineer to build the backbone of our autonomous security platform.
our company builds AI Digital Employees who help cyber teams close the execution gap. Our first AI Digital Employee, Alex, learns, understands and takes away the burden of Identity and Access Management (IAM) tasks - proactively completing the organization's cyber objectives.
About the Role:
Youll design, build, and ship the AI systems behind Alex: production agents that reason over customer identity data, call real tools, and complete IAM tasks end to end. Starting from a cybersecurity need, youll frame the technical problem, choose an approach, and own the solution through production: architecture, implementation, evaluation, deployment, and iteration on real customer behavior.
Youll build on our companys shared agent infrastructure and extend it: new tools and integrations, workflow orchestration, context and memory management, evaluation harnesses, and the guardrails that keep an autonomous agent safe inside a customers environment.
This is a hands-on engineering role, not a research position. The goal is not to prove that an idea can work; it is to make it useful, reliable, and observable for customers in production.
What You'll Do:
Design, implement, and ship AI-powered features for complex cybersecurity workflows, from prototype to production.
Build the systems that make agents work in practice: tool integrations, planning and orchestration logic, context management, structured outputs, and recovery from failures.
Choose the right technical approach for each problem, combining models, deterministic logic, data, and conventional software where appropriate.
Define quality for each use case and build the evaluation pipelines that measure correctness, task completion, consistency, safety, latency, and cost, and wire them into CI and release.
Debug agent behavior in production: trace failures to their root cause in the prompt, tool, data, or architecture, and fix it.
Own the reliability, observability, and cost of the agent systems you build.
Collaborate with cybersecurity experts, product, and platform engineers throughout development.