• Own the agent loop: Step control, planning, retries, error feedback, subagents, and parallel tool calls for long, multi-step tasks.
• Design tools & actions: Build the tools, MCP servers, and skills our agents use - narrow, well-described, permissioned, and safe to call against customer data.
• Engineer context: Decide what the model sees on every step - compaction, memory, retrieval-as-a-tool, and how agents read large enterprise records without drowning.
• Build evals that gate every change: Golden sets, regression suites, and trace-based scoring wired into CI, so no prompt, model, or harness change ships blind.
• Own model choices & the runtime: Route across models on capability, latency, and cost, running new model launches through the eval suite and re-tuning the harness when the frontier moves, with durable sessions, sandboxed execution, nested-trace observability, token budgets, and graceful fallbacks for multi-tenant enterprise customers.
• Own the backend systems: Design services end to end (data model, APIs, storage choice, failure modes), build async pipelines (queues, workers, retries, idempotency, backpressure), and make them fast and cheap at scale (caching, batching, indexing, p95/p99 latency budgets) on multi-tenant AWS with isolation, least-privilege access, PII handling, and audit trails.
• Own it in production: Write the design doc, weigh the trade-offs, defend them in review, and own the service in production.

What Success Looks Like

• Day 30 - Backend: Own one Studio backend service end to end and ship a production change (a new API, a pipeline fix, or a performance improvement) with a measurable result, such as a lower p95 latency or error rate, and join its on-call rotation.
• Day 60 - Fix: Find the top failure mode of an existing agent from its traces and ship a fix that lifts its task success rate by a measurable amount on our eval set (target: +10 points).
• Day 90 - Build: Ship one new agent capability or backend service you designed from scratch, live with at least one customer, with a written design doc and a target metric you set and hit.

What You’ll Need

• Backend & system design: 3+ years building production backend systems with strong system design - you’ve designed and scaled services under real load, picked the data stores, modeled the data, and handled async processing, queues, caching, idempotency, and failure in production. Python preferred.
• Shipped an agent: You’ve shipped at least one LLM agent to real users and can explain its loop, its tools, its failure modes, and the numbers that showed it worked.
• Evals that change decisions: You’ve built evals that changed a decision - you killed, shipped, or reworked something because the eval said so.
• Context & tool design instincts: Strong instincts for context and tool design, able to say why an agent failed by reading its trace.
• Works with coding agents: You use coding agents (Claude Code, Codex, Cursor) as a core part of how you work, and have opinions about what makes a harness good.
• Owns outcomes: A record of owning outcomes - you pick the metric, move it, and report honestly when it doesn’t move.
• Nice to have: Built or contributed to an agent harness, framework, or orchestration layer (open source counts); enterprise B2B in a regulated domain (PII, audit trails, permissions, SOC 2); founder or founding-engineer experience; and any framework (LangGraph, Agent SDKs, Deep Agents) or none - we care about the judgment, not the library.

Compensation and Benefits

• Compensation: Top of market salary + bonuses and equity
• Time off: 49 days paid time off
• Benefits: PTO, full benefits, retirement and wellness plans
• Growth: Professional development support, remote workspace setup bonus
• Team building: Annual company offsites in exciting locations around the world

Location

Certa is a remote-first company and we hire globally. We believe strongly in each team member working from the location that they choose. Should Certers wish to meet and work in person, they have 3 lively office locations they can travel to:

• London
• San Francisco
• Jaipur

The perfect place for Certers to collaborate, co-work, and have face-to-face meetings.

Why Certa

• Category leadership. Certa was named a Leader in the inaugural 2026 Gartner Magic Quadrant for Third-Party Risk Management Tools - recognition that we’re defining the category, not following it.
• Industry recognition. We’ve been honored across the analyst and awards landscape, including Top Tech and Customer Value distinctions in The Hackett Group’s 2026 Risk Management SolutionMap, the ProcureTech100 (Advanced AI and Risk Management categories), and Best Overall eProcurement Software in the FinTech Breakthrough Awards.
• A top place to work. Certa was named one of Forbes’ Best Startup Employers in the US. We’re a fast-growing company where you’ll wear many hats, ship quickly, and shape decisions that matter.
• Real scale with strong backing. We’ve processed over 10 million entities for 100,000+ users across 120+ countries. We’re well-funded by leading investors including Fin Capital, Vertex Ventures, and Point72 Ventures, on the back of an oversubscribed Series B, headed towards Series C.

We’re excited to meet you!