About the Role

We are looking for a Principal AI Architect, Agentic Platform to define the technical foundation for 6sense's next generation of agentic AI.

This is the most senior AI individual contributor role in Engineering. You will establish the architecture, design patterns, runtime standards, evaluation practices, security controls, and governance mechanisms that enable teams across 6sense to build and operate production-grade AI agents safely and efficiently.

You will own the architectural direction for our agentic platform, including orchestration, tools and skills, memory and context, evaluation and observability, security and privacy, guardrails, AI governance, and model strategy.

This is a hands-on Principal role. You will not manage a team, but you will influence architecture across the organization through reference implementations, RFCs, technical reviews, prototypes, mentorship, and deep involvement in complex production systems.

What You'll Own

Agentic Architecture & Design Patterns

• Define the platform-wide architecture for how agents are composed, orchestrated, and executed.
• Establish clear boundaries between reasoning, orchestration, state, tools, and execution.
• Create and maintain an agentic design-pattern catalog covering approaches such as ReAct, plan-and-execute, orchestrator-worker, routing, prompt chaining, fan-out/fan-in, reflection, evaluator-optimizer, and multi-agent handoffs.
• Guide teams toward the simplest architecture that solves the problem, introducing multi-agent systems only when there is a clear technical need.
• Design memory and context architectures covering working, episodic, and semantic memory; context compaction; retrieval grounding; subagent isolation; and tenant-scoped context.
• Publish reference architectures, RFCs, implementation guides, and reusable patterns.
• Lead architecture reviews for agentic systems across Engineering.

Agentic Runtime & Developer Platform

• Own the architecture and standards for LangGraph, including typed state graphs, conditional routing, subgraphs, checkpointing, durable execution, human-in-the-loop workflows, streaming, replay, and time-travel debugging.
• Establish engineering standards for LangChain and determine where framework abstractions provide value versus direct model/provider SDKs.
• Build and evolve the LangSmith practice for tracing, evaluation, prompt management, regression testing, annotation, and experimentation.
• Define the platform contract for agent development, including SDKs, scaffolding, templates, CI/CD gates, replay tooling, and production rollout patterns.
• Establish safe deployment mechanisms such as shadow runs, canary releases, evaluation gates, and emergency kill switches.
• Maintain portability across model and infrastructure providers.

Tools, Skills & Agent Execution

• Own the agent tool and skill registry as a platform capability.
• Define standards for typed tool contracts, versioning, discovery, naming, descriptions, permissions, deprecation, and lifecycle management.
• Architect the MCP layer for 6sense data and actions and establish standards for safely consuming third-party MCP services.
• Address tool-poisoning and untrusted-tool risks as part of the platform architecture.
• Design safe execution patterns using idempotency, retries, compensating transactions, rollback strategies, rate limits, permissions, and spend controls.
• Define agent-to-agent delegation and handoff contracts with authenticated delegation, scope narrowing, and preserved accountability.

Long-Running & Complex Agentic Workflows

• Architect durable, resumable workflows that can survive failures, interruptions, and long execution windows.
• Establish patterns for checkpointing, deterministic replay, failure isolation, saga/compensation, and recovery.
• Define runtime governance including limits on steps, tokens, execution time, cost, and loops.
• Establish stop conditions and escalation mechanisms for stuck, uncertain, or unsafe agents.
• Design human-in-the-loop workflows based on risk tiers while keeping approval experiences practical for users.
• Define reliability metrics such as task success rate, tool-call precision, groundedness, citation accuracy, latency to first useful action, unrecoverable failure rate, and cost per successful outcome.

Security, Privacy & Trust

• Own the security architecture and threat model for agentic systems.
• Apply frameworks such as the OWASP LLM/Agentic Top 10 and MITRE ATLAS to production agent workflows.
• Design protections against prompt injection, excessive agency, tool and memory poisoning, insecure output handling, and supply-chain risks.
• Define agent identity and authorization models using short-lived credentials, least privilege, scoped access, secrets isolation, sandboxing, and egress controls.
• Ensure agents can never access data beyond the permissions of the user or system initiating the workflow.
• Partner with Security and Infrastructure to ensure multi-tenant isolation, auditability, detection, and incident response extend to agent execution.
• Establish adversarial testing and red-team practices, including jailbreak suites, prompt-injection corpora, leakage probes, and security regression tests.

Guardrails, PII & Enterprise AI Controls

• Architect guardrails as enforceable, version-controlled policy rather than relying solely on prompts or procedural controls.
• Build input/output validation, safety classification, groundedness checks, schema enforcement, citation validation, and deterministic policy controls.
• Establish controls for AI-generated go-to-market content, including claim substantiation, disclosures, consent, suppression rules, and jurisdictional requirements.
• Define which actions can be automated and which require human approval.
• Architect PII detection, minimization, redaction/tokenization, field-level encryption, and vendor retention controls across the agent lifecycle.
• Prevent sensitive data leakage through traces, evaluation datasets, prompt caches, memory, vector indexes, and debugging systems.
• Establish appropriate retention, deletion, and data-subject-request propagation mechanisms.
• Make tenant isolation and data residency architectural properties of the platform.

AI Governance & Compliance

• Build the technical foundation for enterprise AI governance, including an agent registry, risk classification, system/model documentation, change management, and automated evidence generation.
• Translate applicable requirements from NIST AI RMF, ISO/IEC 42001, SOC 2, GDPR, and the EU AI Act into practical engineering controls.
• Partner with Security, Legal, Privacy, and Compliance on AI reviews, customer security questionnaires, DPAs, and audits.
• Define governance standards for agent lifecycle management, deployment, monitoring, incident response, and change control.
• Extend existing governance frameworks where they do not adequately address multi-agent and autonomous-system failure modes.

Model Strategy, Cost & Performance

• Define model selection and routing strategies across frontier, smaller, specialized, and fine-tuned models.
• Establish approaches for structured outputs, caching, batching, distillation, and model optimization.
• Define cost and latency budgets at the workflow level.
• Optimize for cost per successful business outcome rather than model cost alone.
• Establish multi-provider strategies, including abstraction, capacity planning, fallbacks, and evaluation-gated model migrations.
• Partner with Product and Engineering to balance capability, reliability, latency, and unit economics.

Technical Leadership & Influence

• Set technical direction across Engineering without direct organizational authority.
• Influence teams through architecture, prototypes, evidence, reference implementations, and technical standards.
• Mentor senior engineers and architects and help raise the organization's agentic engineering capabilities.
• Partner closely with Product, Data Science, Security, Legal, Infrastructure, and IT.
• Contribute to hiring strategy and interview design for advanced AI and agentic engineering roles.
• Represent 6sense with enterprise customers, architecture councils, industry forums, conferences, and technical communities.

Required Qualifications

• 12+ years of experience building and operating production software, including deep distributed-systems experience with consistency, idempotency, backpressure, fault tolerance, and failure recovery.
• 4+ years of hands-on experience building production LLM-based systems.
• 2+ years of experience shipping production agentic systems used by real customers or internal users.
• Deep production experience with LangGraph, LangChain, and LangSmith, or equivalent agent orchestration and evaluation platforms.
• Strong understanding of agentic design patterns and demonstrated judgment in selecting the appropriate level of architectural complexity.
• Strong Python development skills with the ability to write production-quality reference implementations.
• Production experience with retrieval and grounding at scale, including chunking, hybrid search, reranking, citation enforcement, and permission-aware retrieval.
• Demonstrated ownership of an AI evaluation practice, including golden datasets, offline regression testing, LLM-as-judge evaluation with human calibration, and release gating.
• Hands-on experience with security, privacy, and compliance in multi-tenant cloud environments, preferably AWS.
• Experience designing PII protection, tenant isolation, authorization boundaries, prompt-injection defenses, and data-leakage prevention.
• Proven ability to influence architecture across multiple engineering teams without formal authority.
• Strong communication skills with credibility among engineers, executives, security reviewers, and enterprise customers.
• Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

Preferred Qualifications

• Experience building or operating MCP servers and clients.
• Experience with agent-to-agent delegation or emerging agent interoperability protocols.
• Experience in B2B GTM, RevTech, martech, CRM, or revenue intelligence platforms.
• Experience with Salesforce, marketing automation, intent data, identity resolution, or outbound compliance.
• Experience with fine-tuning, preference optimization, distillation, or reinforcement learning applied to agent behavior.
• Experience with large-scale data platforms such as Kafka, Snowflake, Databricks, or Spark.
• Experience building AI platforms operating over billions of data signals.
• Experience scaling AI products through enterprise security and compliance reviews.
• Open-source contributions, patents, technical publications, or industry talks related to AI or agentic systems.

Core Competencies

Systems Thinking · Architectural Restraint · Evidence Over Intuition · Security & Privacy Instinct · Pragmatic Execution · Technical Influence · Clarity

What Success Looks Like

• Production teams adopt a clear, reusable agentic reference architecture and pattern catalog.
• The platform becomes the fastest safe path for teams to build and ship agentic capabilities.
• Every production agent has appropriate tracing, observability, and evaluation coverage.
• Material agent changes are gated by automated evaluation suites with measurable regression baselines.
• Platform-wide guardrails and PII controls are consistently applied across agent execution paths.
• Agent reliability improves measurably across task success rate, latency, failure recovery, and cost per successful outcome.
• Governance and compliance evidence is generated automatically as part of the engineering workflow.
• Production incidents are rare, contained, traceable, and followed by preventive architectural controls.
• New agentic capabilities reach production faster without compromising security, privacy, or reliability.

First 12-Month Success Metrics

• Publish and drive adoption of a platform-wide agentic reference architecture and pattern catalog.
• Establish standardized tracing and evaluation for production agents.
• Implement platform-wide guardrail and PII protection capabilities.
• Establish an agent security and red-team program aligned with major agentic risk categories.
• Improve task success rate, p95 latency, reliability, and cost per successful outcome.
• Reduce time-to-production for new agentic capabilities relative to the current baseline.
• Establish repeatable governance and compliance evidence generation within the development lifecycle.

What This Role Is Not

• Not Engineering Management: This is a Principal individual contributor role with no direct reports.
• Not Pure Research: The focus is production systems, architecture, reliability, and measurable business outcomes.
• Not Governance-Only: You will write code, build reference implementations, and own runtime architecture.
• Not Framework Evangelism: We expect strong judgment about where LangGraph, LangChain, LangSmith, or other frameworks provide value—and where they do not.
• Not Architecture by Committee: You will be expected to make clear technical decisions, validate them with evidence, and drive adoption across teams.

Why This Role Matters

This role sits at the intersection of AI architecture, distributed systems, security, and enterprise software.

You will help define how 6sense builds trustworthy autonomous systems that can act on behalf of customers at enterprise scale. The architecture and standards you establish will influence multiple products and engineering teams and will become the foundation for the next generation of 6sense AI.