Senior AI Engineer

We need to output HTML fragment with sections: headings

for sections like About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. Use

• for any list of duties/requirements/benefits. Use

  for prose. Do NOT repeat job title as heading (not given). Do NOT put Job ID/requisition numbers as headings. Remove boilerplate: cookie/navigation/legal/EEO/equal-opportunity/scam-warning, duplicated lines, application instructions. Preserve all substantive info. Include a section only when posting has real specific content for it; never emit heading with filler. Prefer few substantive sections over many thin ones. We need to parse the posting. Content: - Salary range is: This position is bonus and/or commission eligible. (That's about pay? It says salary range is: This position is bonus and/or commission eligible. No actual numbers. So we have mention of bonus/commission eligible but no salary range. According to rule: never create Pay/Schedule/Benefits sections unless posting actually states them. It states "This position is bonus and/or commission eligible." That's about compensation but not a specific range. Might be considered pay info? The rule: "never create Pay/Schedule/Benefits sections unless the posting actually states them." It does state bonus/commission eligible, which is pay-related. But we need to see if we should include a Pay section. The phrase "Salary range is: This position is bonus and/or commission eligible." It seems incomplete; maybe they omitted actual range. It's not a specific number. The rule says: never emit a heading followed by filler/placeholder text (e.g., "commensurate with experience", "not specified", "N/A", "varies", "TBD"). Here we have "This position is bonus and/or commission eligible." That's not filler; it's a statement about eligibility. Could be considered pay info. However, they didn't give a range. Might be okay to include a Pay section with that statement. But we need to decide. Also Benefits: later they list benefits: "CCC offers competitive compensation and benefits to support you and your families, including: 401K Match Paid time off Annual Incentive Plan Performance Bonus Comprehensive health insurance Adoption Assistance Tuition Reimbursement Wellness Programs Stock Purchase Plan options Employee Resource Groups". That's substantive benefits. So we should include a Benefits section with list. Schedule: not mentioned. So no Schedule section. About the role: there is a paragraph describing CCC and the role. The posting includes: "CCC Intelligent Solutions Inc. (CCC) is a leading cloud platform..." then "The RoleYou will own LLM-powered systems..." etc. So we can have an About the role section (or maybe About CCC?). The instruction: use

  for section headings (e.g. About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule). So we can have About the role, Responsibilities, Requirements, Benefits. Possibly also Qualifications? The posting has Requirements and also "Even Better if You Have:" which could be considered Qualifications or Skills. But we should not create thin sections. We could combine Requirements and Even Better if You Have into Requirements section (maybe split into Required and Preferred). But we need to follow instruction: prefer few substantive sections over many thin ones. So we could have sections: About the role, Responsibilities, Requirements (including both required and preferred), Benefits. Possibly also Skills? The posting includes many specific skills within Requirements. Could treat them as part of Requirements. We must not repeat job title as heading (not given). No Job ID. We must remove boilerplate: like "Interview Policy & Privacy Notice:", "About CCC's Commitment to Employees:", "Here, you belong." etc. Those are boilerplate/EEO? Actually "About CCC's Commitment to Employees:" is maybe not boilerplate but could be considered fluff. The instruction: remove cookie/navigation/legal/EEO/equal-opportunity/scam-warning boilerplate, duplicated lines, and application instructions. The "About CCC's Commitment to Employees:" seems like a values statement; could be considered boilerplate? It's not legal/EEO but could be considered fluff. However, we need to preserve ALL substantive information; do NOT invent or summarize away detail. The values statement might be considered substantive? It's generic. The instruction says prefer few substantive sections over many thin ones. Might be okay to omit that as it's not specific to the role. Also "Learn more about CCC at www.cccis.com." is a link; could be considered boilerplate? Might be okay to keep as part of About the role? It's a reference. Might keep. We need to output only HTML fragment, no /, no markdown fences. Let's extract substantive content: - About CCC: description of company: "CCC Intelligent Solutions Inc. (CCC) is a leading cloud platform for the multi-trillion-dollar insurance economy, creating intelligent experiences for insurers, repairers, automakers, part suppliers, and more. At CCC, we’re making life just work by empowering more than 35,000 businesses with industry-leading technology to get drivers back on the road and to health quickly and seamlessly. We’re pushing boundaries with innovative AI solutions that simplify and enhance the claims and repair journey. Through purposeful innovation and the strength of its connections, CCC technologies empower the people and industry relied upon to keep lives moving forward when it matters most. Learn more about CCC at www.cccis.com." - The Role: "You will own LLM-powered systems and agentic workflows for our customers. These systems automate the routine parts of a claim and guide customers on the rest, so they have to earn that trust with a measured accuracy you can defend as models change and usage grows. Agents run as steps inside deterministic workflows, and privacy and security are design baselines, not review gates. Agentic coding tools are how you move fast. What you add is what they are worst at: system architecture, code quality, security, and the debugging nobody else gets to the bottom of. You own a product area end to end, you define the eval bar it ships against." - Key Responsibilities: list (with duplicates "Key Responsibilities:" repeated). We need to extract each bullet. Responsibilities bullets: 1. Own the delivery of LLM-powered systems in Python and TypeScript, from an ambiguous customer problem, scoped with product managers and data scientists, through production operation. 2. Set the evals and guardrails strategy for your area: what gates a release, what production signals the team watches, and how a change is simulated against historical claims before it ships. 3. Raise the bar for how the team works with agentic coding tools: sharpen the specifications, instruction files, hooks, and permission policies they run under, and hold generated code to the same review standard before it merges. 4. Design the NLP pipelines that turn unstructured claim data into structured data customers can act on, choosing where semantic search, classical NLP, or an LLM fits. 5. Build and operate durable, event-driven, multi-tenant systems in which agents run as steps inside deterministic workflows, designing their failure modes, replay semantics, and cost profile before they show up under load. 6. Own tracing and audit for your area: every model call and agent step recorded, so any recommendation can be reconstructed and cited back to its sources by on-call and auditors alike. 7. Own how claims data is modeled and handled across our relational, document, and graph stores. 8. Set the privacy and security baseline every system in your area starts from: tenant isolation, least-privilege access for agents and their tools, redaction, retention, and what personal and medical data may reach a model provider. 9. Author the design documents for complex systems to get feedback and buy-in, review other engineers' designs and code with the same care, and mentor the engineers in your area. 10. Take part in a shared on-call rotation for the systems you own. - Requirements: list (with duplicate "Requirements:"). Required: 1. 6+ years of professional software engineering experience, including an LLM-powered system you architected, shipped to external customers, and carried through at least one model or prompt migration. 2. Python and TypeScript at the level of setting a team's conventions: the async model, typing strictness, and test strategy for a shared codebase, plus a performance problem you profiled and fixed. 3. An evals and guardrails strategy you set for a product area others built in: where human approval was required, and how production corrections re-entered the evals. 4. A clear account of how you constrain an agentic coding tool's context and verify its output, from daily use of Claude Code, Cursor, GitHub Copilot, or similar on production work, plus changes you turned back, and why. 5. Pipelines you designed that blend LLMs, semantic search, and classical NLP, including a retrieval design you can defend and a case where a classical technique beat an LLM on cost, latency, or reliability. 6. Durable, event-driven systems you designed with deterministic orchestration around non-deterministic model steps: compensating actions, idempotency, backpressure, and event-sourced replay. 7. A production choice among stores such as PostgreSQL, MongoDB, Neo4j, SQL Server, and Cosmos DB, and the ability to defend the data model, partition key, consistency, and tenant-isolation calls you made. 8. Systems architected and operated on Azure or AWS, with CI/CD and infrastructure as code, and hands-on time with a durable workflow engine such as Temporal or the Durable Task Scheduler. 9. Technical design documents you have authored for systems that span more than one team, used to get feedback and buy-in before building, and that those teams then built to. 10. Clear writing and discussion for technical and non-technical audiences: drawing out a customer's real problem and explaining the trade-offs back to them. - Even Better if You Have (preferred): 1. React and TypeScript experience, so you can deliver a full-stack feature end to end. 2. Chat, streaming, and citation-heavy AI experiences especially. 3. Experience with agent frameworks, LangGraph and the Microsoft Agent Framework among them, and with the ways agents reach their tools: the Model Context Protocol (MCP), the Agent2Agent (A2A) protocol, command-line tools, and microservices. 4. Experience with LLM observability and evaluation tooling such as LangSmith, Arize, or Braintrust, and with OpenTelemetry-based tracing. 5. Experience designing A/B tests for AI features. 6. Exposure to the insurance, claims, or automotive repair domains. - What Success Looks Like: (maybe could be considered part of Responsibilities or a separate section? It's more about expectations. Could be omitted as it's somewhat fluff? But it's substantive. However, we prefer few sections. Could incorporate into Responsibilities or Requirements? Might be better to have a separate section "What Success Looks Like" but that's not in the allowed headings list. The allowed headings are About the role, Responsibilities, Requirements, Qualifications, Skills, Benefits, Pay, Schedule. So we could map "What Success Looks Like" into Responsibilities or Requirements. Probably better to add to Responsibilities as additional expectations. But we already have responsibilities list; we could add a paragraph after list summarizing success metrics. However, we should not invent headings not allowed. So we can either omit that section or incorporate into Responsibilities as prose. - Benefits: list as given. - Pay: we have "Salary range is: This position is bonus and/or commission eligible." That's not a range but mentions bonus/commission eligible. Could create a Pay section with that statement. However, the rule says never create Pay/Schedule/Benefits sections unless posting actually states them. It does state bonus/commission eligible, which is pay-related. So we can include Pay section with that statement. But we need to avoid filler like "commensurate with experience". This is not filler; it's a statement. So we can include. - Schedule: not mentioned, so omit. - Qual