{"id":720578,"url":"https://alion.io/job/6sense-principal-ai-architect-agentic-platform","title":"Principal AI Architect, Agentic Platform","company":{"id":2872,"name":"6sense","domain":"6sense.com","url":"https://alion.io/company/6sense","size_band":"1001-5000","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"B","score":75,"open_postings":6,"ghost_share":0,"stale_share":1,"repost_share":0,"time_to_fill_p50_days":29,"computed_at":"2026-11-05T05:54:30Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"lead","employment_type":null,"work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Bengaluru, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":29000,"max_usd":76000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":47},"experience_years_min":12,"visa_sponsorship":false,"relocation_package":false,"has_equity":true,"technologies":[{"name":"Agentic Workflows","optional":false},{"name":"AI Agents","optional":false},{"name":"AWS","optional":false},{"name":"CI/CD","optional":false},{"name":"EU AI Act","optional":false},{"name":"GDPR","optional":false},{"name":"Human-in-the-Loop","optional":false},{"name":"Hybrid Search","optional":false},{"name":"Knowledge Distillation","optional":false},{"name":"LangChain","optional":false},{"name":"LangGraph","optional":false},{"name":"LangSmith","optional":false},{"name":"Least Privilege","optional":false},{"name":"LLM","optional":false},{"name":"LLM Guardrails","optional":false},{"name":"Model Context Protocol","optional":false},{"name":"Model Distillation","optional":false},{"name":"Multi-Agent Systems","optional":false},{"name":"NIST AI RMF","optional":false},{"name":"OWASP","optional":false},{"name":"Python","optional":false},{"name":"Reranking","optional":false},{"name":"SOC 2","optional":false},{"name":"Structured Outputs","optional":false},{"name":"Tokenization","optional":false},{"name":"Apache Kafka","optional":true},{"name":"Databricks","optional":true},{"name":"Fine-tuning","optional":true},{"name":"Reinforcement Learning","optional":true},{"name":"Snowflake","optional":true},{"name":"Spark","optional":true}],"status":"live","first_seen_at":"2024-03-20T11:46:31Z","employer_posted_date":"2026-09-17","last_verified_at":"2026-11-05T17:31:10Z","board_verified":true,"closed_at":null,"days_open":960,"trust":{"level":"stale","repost_count":0,"flags":["stale"],"days_open":959},"description":"Our Mission:\n6sense's mission is to multiply what matters: growth, retention, and efficiency. We envision a future where companies, teams and people reach their full potential.\nOur People:\nPeople 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. \nAbout the Role\nWe are looking for a Principal AI Architect, Agentic Platform to define the technical foundation for 6sense's next generation of agentic AI.\nThis 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.\nYou 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.\nThis 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.\nWhat You'll Own\nAgentic Architecture & Design Patterns\nDefine the platform-wide architecture for how agents are composed, orchestrated, and executed.\nEstablish clear boundaries between reasoning, orchestration, state, tools, and execution.\nCreate 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.\nGuide teams toward the simplest architecture that solves the problem, introducing multi-agent systems only when there is a clear technical need.\nDesign memory and context architectures covering working, episodic, and semantic memory; context compaction; retrieval grounding; subagent isolation; and tenant-scoped context.\nPublish reference architectures, RFCs, implementation guides, and reusable patterns.\nLead architecture reviews for agentic systems across Engineering.\nAgentic Runtime & Developer Platform\nOwn 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.\nEstablish engineering standards for LangChain and determine where framework abstractions provide value versus direct model/provider SDKs.\nBuild and evolve the LangSmith practice for tracing, evaluation, prompt management, regression testing, annotation, and experimentation.\nDefine the platform contract for agent development, including SDKs, scaffolding, templates, CI/CD gates, replay tooling, and production rollout patterns.\nEstablish safe deployment mechanisms such as shadow runs, canary releases, evaluation gates, and emergency kill switches.\nMaintain portability across model and infrastructure providers.\nTools, Skills & Agent Execution\nOwn the agent tool and skill registry as a platform capability.\nDefine standards for typed tool contracts, versioning, discovery, naming, descriptions, permissions, deprecation, and lifecycle management.\nArchitect the MCP layer for 6sense data and actions and establish standards for safely consuming third-party MCP services.\nAddress tool-poisoning and untrusted-tool risks as part of the platform architecture.\nDesign safe execution patterns using idempotency, retries, compensating transactions, rollback strategies, rate limits, permissions, and spend controls.\nDefine agent-to-agent delegation and handoff contracts with authenticated delegation, scope narrowing, and preserved accountability.\nLong-Running & Complex Agentic Workflows\nArchitect durable, resumable workflows that can survive failures, interruptions, and long execution windows.\nEstablish patterns for checkpointing, deterministic replay, failure isolation, saga/compensation, and recovery.\nDefine runtime governance including limits on steps, tokens, execution time, cost, and loops.\nEstablish stop conditions and escalation mechanisms for stuck, uncertain, or unsafe agents.\nDesign human-in-the-loop workflows based on risk tiers while keeping approval experiences practical for users.\nDefine 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.\nSecurity, Privacy & Trust\nOwn the security architecture and threat model for agentic systems.\nApply frameworks such as the OWASP LLM/Agentic Top 10 and MITRE ATLAS to production agent workflows.\nDesign protections against prompt injection, excessive agency, tool and memory poisoning, insecure output handling, and supply-chain risks.\nDefine agent identity and authorization models using short-lived credentials, least privilege, scoped access, secrets isolation, sandboxing, and egress controls.\nEnsure agents can never access data beyond the permissions of the user or system initiating the workflow.\nPartner with Security and Infrastructure to ensure multi-tenant isolation, auditability, detection, and incident response extend to agent execution.\nEstablish adversarial testing and red-team practices, including jailbreak suites, prompt-injection corpora, leakage probes, and security regression tests.\nGuardrails, PII & Enterprise AI Controls\nArchitect guardrails as enforceable, version-controlled policy rather than relying solely on prompts or procedural controls.\nBuild input/output validation, safety classification, groundedness checks, schema enforcement, citation validation, and deterministic policy controls.\nEstablish controls for AI-generated go-to-market content, including claim substantiation, disclosures, consent, suppression rules, and jurisdictional requirements.\nDefine which actions can be automated and which require human approval.\nArchitect PII detection, minimization, redaction/tokenization, field-level encryption, and vendor retention controls across the agent lifecycle.\nPrevent sensitive data leakage through traces, evaluation datasets, prompt caches, memory, vector indexes, and debugging systems.\nEstablish appropriate retention, deletion, and data-subject-request propagation mechanisms.\nMake tenant isolation and data residency architectural properties of the platform.\nAI Governance & Compliance\nBuild the technical foundation for enterprise AI governance, including an agent registry, risk classification, system/model documentation, change management, and automated evidence generation.\nTranslate applicable requirements from NIST AI RMF, ISO/IEC 42001, SOC 2, GDPR, and the EU AI Act into practical engineering controls.\nPartner with Security, Legal, Privacy, and Compliance on AI reviews, customer security questionnaires, DPAs, and audits.\nDefine governance standards for agent lifecycle management, deployment, monitoring, incident response, and change control.\nExtend existing governance frameworks where they do not adequately address multi-agent and autonomous-system failure modes.\nModel Strategy, Cost & Performance\nDefine model selection and routing strategies across frontier, smaller, specialized, and fine-tuned models.\nEstablish approaches for structured outputs, caching, batching, distillation, and model optimization.\nDefine cost and latency budgets at the workflow level.\nOptimize for cost per successful business outcome rather than model cost alone.\nEstablish multi-provider strategies, including abstraction, capacity planning, fallbacks, and evaluation-gated model migrations.\nPartner with Product and Engineering to balance capability, reliability, latency, and unit economics.\nTechnical Leadership & Influence\nSet technical direction across Engineering without direct organizational authority.\nInfluence teams through architecture, prototypes, evidence, reference implementations, and technical standards.\nMentor senior engineers and architects and help raise the organization's agentic engineering capabilities.\nPartner closely with Product, Data Science, Security, Legal, Infrastructure, and IT.\nContribute to hiring strategy and interview design for advanced AI and agentic engineering roles.\nRepresent 6sense with enterprise customers, architecture councils, industry forums, conferences, and technical communities.\nRequired Qualifications\n12+ years of experience building and operating production software, including deep distributed-systems experience with consistency, idempotency, backpressure, fault tolerance, and failure recovery.\n4+ years of hands-on experience building production LLM-based systems.\n2+ years of experience shipping production agentic systems used by real customers or internal users.\nDeep production experience with LangGraph, LangChain, and LangSmith, or equivalent agent orchestration and evaluation platforms.\nStrong understanding of agentic design patterns and demonstrated judgment in selecting the appropriate level of architectural complexity.\nStrong Python development skills with the ability to write production-quality reference implementations.\nProduction experience with retrieval and grounding at scale, including chunking, hybrid search, reranking, citation enforcement, and permission-aware retrieval.\nDemonstrated ownership of an AI evaluation practice, including golden datasets, offline regression testing, LLM-as-judge evaluation with human calibration, and release gating.\nHands-on experience with security, privacy, and compliance in multi-tenant cloud environments, preferably AWS.\nExperience designing PII protection, tenant isolation, authorization boundaries, prompt-injection defenses, and data-leakage prevention.\nProven ability to influence architecture across multiple engineering teams without formal authority.\nStrong communication skills with credibility among engineers, executives, security reviewers, and enterprise customers.\nBachelor's degree in Computer Science, Engineering, or a related field, or equivalent practical experience.\nPreferred Qualifications\nExperience building or operating MCP servers and clients.\nExperience with agent-to-agent delegation or emerging agent interoperability protocols.\nExperience in B2B GTM, RevTech, martech, CRM, or revenue intelligence platforms.\nExperience with Salesforce, marketing automation, intent data, identity resolution, or outbound compliance.\nExperience with fine-tuning, preference optimization, distillation, or reinforcement learning applied to agent behavior.\nExperience with large-scale data platforms such as Kafka, Snowflake, Databricks, or Spark.\nExperience building AI platforms operating over billions of data signals.\nExperience scaling AI products through enterprise security and compliance reviews.\nOpen-source contributions, patents, technical publications, or industry talks related to AI or agentic systems.\nCore Competencies\nSystems Thinking · Architectural Restraint · Evidence Over Intuition · Security & Privacy Instinct · Pragmatic Execution · Technical Influence · Clarity\nWhat Success Looks Like\nProduction teams adopt a clear, reusable agentic reference architecture and pattern catalog.\nThe platform becomes the fastest safe path for teams to build and ship agentic capabilities.\nEvery production agent has appropriate tracing, observability, and evaluation coverage.\nMaterial agent changes are gated by automated evaluation suites with measurable regression baselines.\nPlatform-wide guardrails and PII controls are consistently appli...","description_format":"text","description_chars":15891,"description_truncated":true,"requirements":{"experience_years_min":12,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"bachelor","optional":false},"security_clearance":false,"languages":[]},"benefits":["Parental leave","Stock options"],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Sales Enablement","Marketing Automation","Lead Generation","Marketing & Sales AI"],"lifecycle":[{"event":"open","at":"2026-09-11T07:06:36Z"}],"visa":[],"liveness":{"score":8,"band":"cold","label":"Long shot","p_open":1,"p_active":0.279,"p_room":0.28,"age_days":959,"expected_fill_days":29,"reasons":["conf:4","velocity","win:tail","crowd:"],"computed_at":"2026-11-05T05:54:30Z"},"pay":null,"html_url":"https://alion.io/job/6sense-principal-ai-architect-agentic-platform","json_url":"https://alion.io/job/6sense-principal-ai-architect-agentic-platform.json","meta":{"generated_at":"2026-11-05T18:38:21Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":24669,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-11-06T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":2872},"rest":"https://alion.io/mcp/rest/get_company?id=2872"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2F6sense-principal-ai-architect-agentic-platform"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2F6sense-principal-ai-architect-agentic-platform"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2F6sense-principal-ai-architect-agentic-platform"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/6sense-principal-ai-architect-agentic-platform\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2F6sense-principal-ai-architect-agentic-platform"}],"agent":{"mcp":"https://alion.io/mcp/jobs","mcp_open":"https://alion.io/mcp/open","next":[{"tool":"get_job","arguments":{"id":720578}},{"tool":"search_jobs","arguments":{"company":"6sense.com","detail":"compact"}},{"tool":"match_people","arguments":{"job_id":720578},"note":"people open to offers who fit this vacancy"}],"note":"The same data through MCP tools: https://alion.io/mcp/open needs no sign-in (compact searches, postings, people); https://alion.io/mcp with an Alion account has everything. Docs: https://alion.io/developers"}}