Sr. Software Engineer

Our Mission: 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. Our People: 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. Senior AI Engineer, Agentic Platform Location: San Francisco Bay Area or Austin, TX (Hybrid) About the Role 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 expanding an ecosystem that external agents, clients, and partners can connect to. You'll work across the full path from a customer's agent to 6sense data and actions, including APIs, tools, MCP, orchestration, context, evaluation, and security. 6sense is working to become the default Contextual Intelligence layer for B2B, and 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. What You'll Own Agents and Orchestration

Extend LangGraph orchestrators with typed state, conditional routing, subgraphs, checkpointing, durable execution, and human-in-the-loop workflows. Select and implement routing, orchestrator-worker, plan-and-execute, reflection, and multi-agent handoff patterns based on business needs. Run agents headless through API-first and MCP-first architectures across in-app, chat, workflow, and partner surfaces from a shared core. Build and maintain reusable components for state management, memory, tool-calling, and agent-to-agent delegation with scoped permissions.

APIs, Tools, and MCP

Evolve the APIs and tools agents use to access 6sense data and take action for both human and LLM consumers. Optimize tool design for agent success, including naming, descriptions, schemas, response formats, error handling, and token efficiency. Re-design and scale the MCP layer for production workloads, including concurrency, per-tenant quotas, latency budgets, caching, graceful degradation, backward compatibility, and adoption of emerging MCP capabilities. Onboard external MCP clients, AI assistants, agent platforms, and partners. Develop integration guides and reference clients and define trust boundaries for third-party MCP server integrations. Strengthen platform reliability through idempotency, retries, rate limits, permissions, spend controls, and standards for tool contracts, versioning, and discovery.

Context and Evaluation

Partner with the Contextual Intelligence team to expose context through MCP, APIs, and tools, enabling a unified context layer across all customer touchpoints. Define and enforce contracts around returned data, freshness, provenance, and tenant and user-level access controls. Improve permission-aware retrieval and grounding through chunking, hybrid search, reranking, citations, context assembly, and memory management within token and latency constraints. Expand evaluation frameworks using golden datasets, tool-selection accuracy, tool-call accuracy, end-to-end task success metrics, regression testing, release gates, and context quality measurements. Enhance tracing and usage analytics while reporting on task success rates, tool-call precision, groundedness, latency, and cost efficiency.

Security, Privacy, and Trust

Make security a first-class consideration across every tool, API, agent, and MCP change. Review your own and teammates' work for vulnerabilities and security risks. Enforce tenant isolation and user-level authorization for all requests while maintaining short-lived, scoped credentials. Protect against prompt injection, tool poisoning, excessive agent autonomy, and data leakage through outputs, traces, and logs. Establish runtime guardrails around steps, tokens, execution time, and spend.

Customers and Engineering Excellence

Investigate and resolve customer-reported issues across agents, tools, models, and downstream systems. Participate in customer and partner technical discussions and support enablement teams through guidance, demonstrations, and documentation. Write design documents, evaluate trade-offs, conduct code reviews, mentor engineers, and participate in on-call and incident response rotations. Stay current with developments in MCP, agent frameworks, and model capabilities, prototyping promising technologies and sharing evidence-based recommendations.

What You'll Bring

5+ years of experience building and operating production software systems, with strong distributed systems fundamentals including idempotency, fault tolerance, backpressure, and failure recovery. 2+ years of experience building production LLM-powered systems, including customer-facing agents. Strong Python development skills and production experience with LangGraph or a comparable orchestration framework. Experience designing APIs and tool interfaces for LLM consumers, including schemas, descriptions, error handling, and tool selection optimization. Direct MCP experience is strongly preferred. Experience scaling customer- or partner-facing platforms, including authentication, rate limiting, versioning, and backward compatibility. Hands-on experience with retrieval, grounding, and LLM evaluation frameworks. Experience building multi-tenant, security-sensitive cloud systems (AWS preferred), includi