FirstWork

Lead and own backend subsystems for AI-powered document processing and workflow automation, collaborating across teams and shipping production-grade features. | 5+ years backend engineering with system ownership, strong SQL and distributed systems knowledge, leadership experience, and clear communication skills. | FirstWork is building the next generation of agentic AI products for frontline hiring, the work that gets roughly 80% of the world's workforce hired, verified, and paid. We're looking for a Senior Software Engineer to own a significant part of the platform and ship the AI capability that runs on top of it. In this role, you'll lead projects end to end, from the first design doc through rollout and follow-through, collaborating closely with product managers, designers, and the engineers building our AI infrastructure. You'll set the standard for the engineers around you and see your work meet live enterprise volume every week. The scale we run at ~50,000 workers a week move through our hiring and onboarding flows. 2.5 million API requests a day across the platform. Millions of document pages a year processed by AI agents, across 40+ countries and a dozen-plus languages. Single accounts running hundreds of thousands of AI document extractions in one month, and compliance engines evaluating thousands of customer-specific rules per tenant. Global staffing, logistics, healthcare, marketplace, and employment platforms across the US, UK, EU, LATAM, and India. Billing on work performed, per document validated and per agent action executed, which makes product design, cost per unit, and gross margin one conversation. What you'll do Own a subsystem end to end document processing, workflow automation, compliance rules, communications, or integrations; and lead the projects inside it from design doc through rollout. Ship AI agent capability into production: extraction and validation pipelines, confidence handling, human review routing, and the feedback loop that raises accuracy document type by document type. Build AI browsing agents that drive government and third-party portals through the browser, where the only interface is the UI. Own accuracy and cost for the AI you ship, across prompts, structured output, evaluation, model selection, and spend per document. Design and evolve the REST APIs and webhooks that customer ATS, HR, and payroll integrations run on. Write durable async workflows in Temporal for automations, AI jobs, and bulk actions, built so that a retry is always safe. Design schema and data models that hold up as tenants, volume, and product surface grow. Improve latency and throughput with production evidence: profile it, fix it, prove the win. Raise the engineering bar around you through design review, code review, and mentoring. Work directly with product and operations to turn a customer's real process into product. What we need 5+ years of professional backend engineering experience, including a system you owned end to end. Strong SQL and relational data modelling: you design schema before code, and you read query plans when it counts. Solid distributed systems fundamentals across queues, async workers, idempotency, retries, and partial failure. A track record of leading a project across several engineers and landing it. Care for correctness in multi-tenant systems, where every query stays scoped to a single customer. Clear written communication: design docs, pull requests, and incident writeups others can follow. Comfort with ambiguity, and the judgement to define a problem alongside solving it. Nice to have Strong Python, with meaningful time in Django and Django REST Framework or a close equivalent. Hands-on experience shipping LLM- or ML-powered features to production. Experience with agentic systems, workflows, or orchestration frameworks. Browser automation at scale with Playwright or similar. Temporal, Celery, Airflow, or another durable execution engine. PostgreSQL beyond CRUD: partial indexes, partitioning, replicas, connection pooling. Evaluation harnesses for LLM features, and cost control at volume. Regulated domains such as identity, payroll, healthcare, fintech, or compliance. HR tech, marketplaces, or other high-volume operational products. Experience in an AI-first, fast-moving product environment. Familiarity with AI-assisted development tools such as Claude. About FirstWork FirstWork is an applied AI company building the HR operations platform behind frontline hiring, the largest, least automated, and most heavily regulated labour market in the world. One system carries a worker from application through onboarding, compliance verification, training, and payroll, for hundreds of enterprise customers. We are AI-native. Our document agents read and validate credentials against policy. Our browsing agents drive government portals through the browser, where the only interface is the UI. Our voice and conversational agents screen and follow up with candidates. Our rule engines adjudicate compliance decisions and produce the audit trail behind them. Our agents are doing regulated work in production today. Firstwork is an equal opportunity employer. We evaluate applicants without regard to race, color, religion, sex, national origin, age, disability, or any other protected status.

Lead architecture and development of scalable AI-driven backend systems with a focus on reliability, compliance, and performance. | 8+ years backend experience, scaling architectures, relational DB expertise, AI/LLM production experience, and strong distributed systems knowledge. | FirstWork is building the next generation of agentic AI products for frontline hiring, the work that gets roughly 80% of the world's workforce hired, verified, and paid. We're looking for a Staff Backend Engineer to architect the systems that let those agents run at the next order of magnitude, and to build the new product lines we are launching with AI designed-in from the start. In this role, you'll set the technical direction for a core domain and work closely with product, design, and engineering leadership to get intelligent systems into a shape customers can configure and rely on. This is a hands-on architecture role: you'll still write code, and you'll see your decisions tested against live enterprise volume. The challenges ahead are scaling throughput, latency, and data volume as usage compounds, and keeping AI agents accurate, reliable, and economical as that happens. The scale we run at ~50,000 workers a week move through our hiring and onboarding flows. 2.5 million API requests a day across the platform. Millions of document pages a year processed by AI agents, across 40+ countries and a dozen-plus languages. Global staffing, logistics, healthcare, marketplace, and employment platforms across the US, UK, EU, LATAM, and India. Billing on work performed, per document validated and per agent action executed, which makes product design, cost per unit, and gross margin one conversation. What you'll do Take end-to-end ownership of core domain: the agent runtime, the compliance and rules engine, the worker data model, or integrations. Push LLMs and agentic AI deeper into the product, and draw the line between what belongs in inference and what belongs in deterministic, auditable rules. Design the safety properties of agents that act in external systems, including idempotency, retries, isolation, and human escalation. Build the evaluation and accuracy infrastructure that makes AI decisions defensible in a regulated context. Keep inference viable at scale through model routing, caching, and batching, with cost per transaction as a tracked metric. Design data models with long-lived constraints, including audit logs, compliance clocks, and credential lifecycles. Drive the data architecture roadmap: read replicas, logical sharding, CDC-fed projections, and a search tier. Enforce multi-tenancy, permissions, and audit trails as invariants guaranteed by design and by test. Act as a technical lead through design review, incident command, and mentoring senior engineers. Work directly with product and customers to turn bespoke requests into platform capabilities. What we need 8+ years of professional backend engineering experience. Experience at a company that outgrew its first architecture, and a hand in scaling it incrementally. Deep relational database expertise, including diagnosing saturation in production. Production experience with LLM or vision-model systems: evaluation, accuracy, cost control, and fallback design. Strong distributed systems judgement across idempotency, retries, queue lag, and partial failure. Experience with multi-tenant, configurable products. A measurement-first approach: profiles and traces before opinions. Influence through clear writing and demonstrated results. Nice to have Built agentic systems where an agent takes real action in an external system. Temporal or another durable execution engine at production scale. Event-driven architecture and CDC pipelines feeding read stores. Rules engines, policy-as-code, or workflow orchestration. Compliance, identity, payroll, or financial infrastructure background. Experience platformizing a single-vertical product for additional verticals. Experience in an AI-first, fast-moving product environment. Familiarity with AI-assisted development tools such as Claude. About FirstWork FirstWork is an applied AI company building the HR operations platform behind frontline hiring, the largest, least automated, and most heavily regulated labour market in the world. One system carries a worker from application through onboarding, compliance verification, training, and payroll, for hundreds of enterprise customers. We are AI-native. Our document agents read and validate credentials against policy. Our browsing agents drive government portals through the browser, where the only interface is the UI. Our voice and conversational agents screen and follow up with candidates. Our rule engines adjudicate compliance decisions and produce the audit trail behind them. Our agents are doing regulated work in production today. Firstwork is an equal opportunity employer. We evaluate applicants without regard to race, color, religion, sex, national origin, age, disability, or any other protected status.