<div class="content-intro"><p><strong>Our Mission:</strong></p> <p>6sense's mission is to multiply what matters: growth, retention, and efficiency. We envision a future where companies, teams and people reach their full potential.</p> <p><strong>Our People:</strong></p> <p>People are the heart and soul of 6sense. We serve with passion and purpose. We live by our Being 6sense values of Win as One Team, Stay Curious, Do The Right Thing, Own the Outcome, and Create Belonging. Every 6sensor plays a part in defining the future of our industry-leading technology. 6sense is a place where difference-makers roll up their sleeves, take risks, act with integrity, and measure success by the value we create for our customers. We want 6sense to be the best chapter of your career. </p></div><h2>Job Description</h2> <p>6sense has agents and an MCP server in production today, used by real customers. This role takes them further by building more capable agents, strengthening the API and tool layer, and creating an ecosystem that external agents, clients, and partners can connect to.</p> <p>You'll work across the full journey from a customer's agent to 6sense data and actions—including APIs, tools, MCP, orchestration, context, evaluation, and security.</p> <p>6sense is working to become the default Contextual Intelligence layer for B2B. Agents and MCP are how that context reaches customers, partners, and their AI tools. You'll partner closely with the team building contextual intelligence, write production Python daily, own multi-month projects, support the teams and customers who depend on these systems, and keep the platform current as the agent tooling landscape evolves.</p> <h2>What You'll Own</h2> <h3>Agents and Orchestration</h3> <ul> <li> <p>Extend LangGraph orchestrators with typed state, conditional routing, subgraphs, checkpointing, durable execution, and human-in-the-loop steps.</p> </li> <li> <p>Choose among routing, orchestrator-worker, plan-and-execute, reflection, and multi-agent handoff patterns based on the problem.</p> </li> <li> <p>Run agents headless—API- and MCP-first—across in-app, chat, workflow, and partner surfaces from one shared core.</p> </li> <li> <p>Maintain reusable components for state, memory, tool-calling, and agent-to-agent delegation with scoped permissions.</p> </li> </ul> <h3>APIs, Tools, and MCP</h3> <ul> <li> <p>Evolve the APIs and tools agents use to read 6sense data and take action, for both human and LLM callers.</p> </li> <li> <p>Tune tool design for agent success, including names, descriptions, schemas, response shapes, error messages, and token-efficient outputs.</p> </li> <li> <p>Redesign and scale the MCP layer for production workloads, including concurrency, per-tenant quotas, latency budgets, caching, and graceful degradation, while maintaining backward compatibility and adopting new specification capabilities as they mature.</p> </li> <li> <p>Onboard external MCP clients, AI assistants, agent platforms, and partners. Write integration guides and reference clients, and define how 6sense consumes third-party MCP servers, including trust boundaries.</p> </li> <li> <p>Harden execution with idempotency, retries, rate limits, permissions, and spend controls. Maintain standards for tool contracts, versioning, and discovery.</p> </li> </ul> <h3>Context and Evaluation</h3> <ul> <li> <p>Partner with the Contextual Intelligence team to expose context to agents through MCP, APIs, and tools, ensuring one context layer serves every surface. Establish contracts defining what each call returns, how fresh the information is, where it comes from, and how it is scoped to the tenant and user.</p> </li> <li> <p>Improve permission-aware retrieval and grounding through chunking, hybrid search, reranking, and citations. Optimize context assembly and memory within token and latency limits.</p> </li> <li> <p>Extend evaluation using golden datasets, tool-selection and tool-call accuracy, end-to-end task success, regression suites, and release gates, including context-quality measures.</p> </li> <li> <p>Expand tracing and usage analytics, and report on task success rate, tool-call precision, groundedness, latency, and cost per successful outcome.</p> </li> </ul> <h3>Security, Privacy, and Trust</h3> <ul> <li> <p>Make security a first consideration in every tool, API, agent, and MCP change, and review your own and teammates' work for vulnerabilities.</p> </li> <li> <p>Enforce tenant isolation and user-level authorization on every call so agents never access data beyond the caller's permissions. Maintain short-lived, scoped credentials.</p> </li> <li> <p>Defend against prompt injection, tool poisoning, excessive agency, and data leakage through tool outputs, traces, and logs. Set runtime limits on steps, tokens, time, and cost.</p> </li> </ul> <h3>Customers and Engineering Craft</h3> <ul> <li> <p>Triage and debug customer-reported issues across agents, tools, models, and downstream systems, identify root causes, and deliver fixes.</p> </li> <li> <p>Participate in customer and partner technical calls, and support enablement teams with guidance, demos, and documentation.</p> </li> <li> <p>Write design documents that clearly explain assumptions and trade-offs, review code