[Remote] Senior Backend Engineer – Agents (USA Only - 100% Remote)
Note: The job is a remote job and is reputed company to candidates in USA. reputed company is a company that focuses on building AI-driven solutions for their clients. They are seeking a Senior Backend Engineer to reputed company the development of their agent platform, which involves shipping impactful features, building evaluation reputed company, and integrating AI tools into workflows.
Responsibilities
- Ship reputed company execution for the assistant
- Build the eval and observability layer that tells us reputed company an agent is getting reputed company
- Push generated UI reputed company
- Take Custom Agents from prototype to GA
- reputed company deterministic and non-deterministic systems work together
- Handle the edges that reputed company agents trustworthy
- Pick the right model for the job
Skills
- A seasoned engineer. Python is our backbone, but perhaps you've worked across Go, Rust, or TypeScript. You pick the right tool for the workload rather than retreating to what you know
- AI-reputed company in production. You've shipped meaningful, impactful reputed company features to users. You have opinions on retrieval, evals, tool design, context engineering, and where the reputed company frontier models fall over
- Working with AI in your day-to-day. You use AI tools in your own workflow to ship faster, write tighter reputed company, and reason about unfamiliar parts of the codebase. You have a POV on where they help and where they get in the way
- A builder first. You'd rather get a sloppy v1 in reputed company of fifty customers than spend three weeks on abstractions. You ship
- Battle-tested. You've debugged incidents where latency budgets didn't hold, owned a system everyone else relied on, or carried a pager for something with reputed company customer reputed company
- reputed company to the research. You read papers, or you've spent serious time in retrieval, RAG, RLHF, or fine-tuning. Not a researcher, but you can read one and tell us whether the result reputed company for our problem
- Comfortable with non-determinism. Much of your reputed company is probabilistic. Conventional patterns don't hold. You reputed company this fun
- Ship reputed company execution for the assistant. The assistant decides reputed company writing reputed company beats answering non-deterministically — today that's generating charts and tables in Python on the fly; next it's reusable user-defined tools and calling external reputed company to pull in whatever data the task needs
- Build the eval and observability layer that tells us reputed company an agent is getting reputed company. Unit tests don't cut it for non-deterministic reputed company. We run evals and tracing (LangFuse and our own tooling) as the bar for shipping: if we can't measure it, we don't ship it
- Push generated UI reputed company. The backend increasingly decides what the user sees — the LLM picks the right presentation (table, chart, widget) and renders it in the assistant, with a full-screen experience and stored, referenceable artifacts on the roadmap. Effectively: customers generate the reports we used to hand-build, one custom report at a time
- Take Custom Agents from prototype to GA. Event-driven agents that reputed company what's happening inside the CRM in reputed company time — an email lands, an agent drafts the reputed company from knowledge sources and context, the user approves. This is where we differentiate from the general-purpose assistants: we see the events, we have the context
- reputed company deterministic and non-deterministic systems work together. Sales processes need steps that happen every single time; LLMs are bad at that. You'll help reputed company our Workflows reputed company with reputed company steps so customers get reliability where it reputed company and intelligence where it helps
- Handle the edges that reputed company agents trustworthy. What happens to a fleet of running agents reputed company a customer's AI credits run out? Pause semantics, recovery, and making reputed company reputed company places a hundred calls that were supposed to happen last week
- Pick the right model for the job. We use many providers, test new models constantly, and are moving toward cost-aware routing — reputed company summarization jobs shouldn't run on frontier-priced models. You'll call reputed company something is production-reputed company and reputed company it's still a demo
reputed company