Senior/Staff Software Engineer, Data Lifecycle

Description

The company makes a conversational AI platform that lets large brands deploy AI agents for customer interactions over voice, chat, email, SMS and other channels.

Customers include large brands in car rental, airlines, payments, health tech and software, and the platform runs live for them across chat, voice, email and SMS.

The Data Lifecycle team builds the systems that decide how sensitive customer data is stored, who may access it, how it is redacted and when it is deleted. The goal is privacy rules that customers can configure and rely on.

The team is central to how the company scales. The AI agents handle sensitive information in conversations, tool calls and customer systems, so the frameworks need to protect that data consistently across the platform while keeping the context customers need. A production failure becomes a guardrail, test or tool that catches the problem everywhere else.

The role is a Senior or Staff Software Engineer position on this team.

Responsibilities

• Design and build the platform infrastructure that lets customers control collection, retention, redaction and deletion of their data, with strong engineering underneath and abstractions that work across varied enterprise requirements without per-customer forks.
• Work day to day with product management, governance and security to understand customer requirements, define data handling guarantees, review designs and carry work through launch.
• Stay close to customers to understand their privacy and operational needs and confirm that what you build fits them.
• Own features end to end, from architecture through deployment and later iteration, including checking that sensitive data is protected and that each action actually completes.
• Build PII handling and redaction systems that find and protect sensitive information in conversations, agent traces and other customer data.
• Design configuration abstractions for redaction and retention policies that balance enterprise flexibility with clear, safe defaults.
• Build reliable deletion workflows that reach across storage systems and derived data, with retries, verification and visibility into failures.
• Build self-serve tools and APIs so customers can configure, test and understand their lifecycle policies without an engineer.
• Build LLM-backed systems that scan for and detect data anomalies and policy violations.
• Train and or tune models to detect data in various forms, including PII and PHI.
• Extend redaction and identification to multimodal agents, covering images, attachments, voice notes and documents.
• Build monitoring and audit tooling that shows what data was processed, what remains and where a policy failed, without exposing sensitive information.
• Run lifecycle systems at scale, including backfills, partial failures and safe rollouts, since your work touches critical flows for Fortune 100 companies.

Requirements

• At least 4 years building software products, with strong product thinking.
• Proficient in Python and comfortable working across the full stack.
• Experience designing reliable backend systems and data pipelines, including asynchronous processing, retries and failure recovery.
• Understanding of operational maturity for critical systems, including observability and monitoring.
• Ability to reason about where data flows, where copies persist and what happens when one step of a workflow fails.
• Strong comfort debugging failures in deep technology stacks, using whatever tools get you to the answer.
• Good judgment about when to ship quickly and when correctness, privacy and irreversible operations call for slowing down.
• An understanding of durable, fault-tolerant systems is key.
• Even better: experience with PII detection, redaction, tokenization or secure handling of sensitive data.
• Even better: experience building data retention, deletion or privacy request workflows across multiple storage systems.
• Even better: experience building security-sensitive systems such as authentication, authorization and data access controls.
• Even better: familiarity with GDPR, CCPA or PCI and turning those requirements into engineering controls.
• Even better: background with LLMs, evals or AI agent systems, especially handling sensitive data in model inputs, outputs and traces.
• Even better: experience with observability, audit trails or operational tooling for large-scale data systems.
• Even better: experience working with sensitive data in voice, images or other non-text formats.

Conditions

Base salary range of $200K to $400K, plus equity.

The range reflects expected pay. The exact figure depends on experience, skills and scope, with room for candidates who show exceptional impact.

Equity is offered on top of base salary. Final pay may vary by location within the United States.

The role is in the office, as the company works in person.

Benefits

• Medical, dental and vision coverage for you and your family.
• Life insurance and disability benefits.
• A retirement plan such as a 401K or pension.
• Parental leave.
• Fertility and family building support through Carrot.
• A monthly stipend for wellness, lifestyle and work-life balance.
• Daily lunches and snacks in the office.
• A flexible take-what-you-need vacation policy, subject to local rules. UK employees receive 25 days of statutory leave.
• Benefits are set out in company policy, may differ by location and can change under the applicable compensation and benefits plans.