Software Engineer, AI / Backend Systems: build dependable AI systems.

What will you build?

CiteSurge measures how brands appear in AI-generated answers and turns that evidence into dependable product decisions. You will build the backend and data systems that keep multi-engine observations useful, reviewable, and safe for customer-facing products. The work is a combination of applied AI, backend engineering, data quality, and product delivery.

You will move between difficult evidence cases, typed domain models, APIs, workers, and operational tools. Each project has to preserve uncertainty, communicate evidence quality clearly, and protect customer data and proprietary methods. The goal is software that helps expert teams make defensible decisions even when external AI products change.

Which problems will you solve?

How do we measure across AI answer surfaces?

Multi-engine measurement is the work of making answer, mention, and citation evidence consistent enough for responsible review. You will help preserve what was observed, the context needed to interpret it, and a neutral unavailable state when evidence cannot support a conclusion. The product must let customers compare supported observations without pretending that every answer surface behaves the same way. This is applied engineering for a customer-facing evidence product, not a public description of CiteSurge's private implementation.

How should the product handle ambiguous brand names?

Entity judgment is a core evidence-quality problem. A short or generic name may identify a customer, another organization, a product, or ordinary language. You will improve how CiteSurge preserves uncertainty and presents ambiguous evidence without silently forcing a match. A useful result has to help reviewers understand what is confirmed, what remains unresolved, and what should be excluded from a decision. Strong candidates are comfortable testing that distinction against difficult cases and explaining the result in plain language.

What makes evidence useful for decisions?

Evidence quality is the difference between a persuasive interface and a dependable product. You will test whether outputs are clear, supported, and comparable, then help customer-facing teams understand the limits of each conclusion. The work keeps observed change distinct from causal attribution and makes material uncertainty visible to the people using the evidence. A strong solution should improve decision confidence without hiding ambiguity behind a score or a polished summary.

How do reliable product systems behave?

A reliable CiteSurge system is useful under partial failure and remains clear as external AI products change. You will build backend, data, and reporting services that keep customer-facing workflows stable, surface evidence quality, and support accountable decisions. The role rewards engineers who can move from a difficult product case to a durable technical design, verify the behavior, and document the tradeoffs. Operational quality, privacy, and customer-safe failure states are part of the product rather than cleanup work.

What skills matter?

• Strong backend engineering in TypeScript, Go, Python, or a comparable systems language.
• Experience designing APIs, data models, workers, integrations, and observable production services.
• Practical work with LLMs, information extraction, retrieval, evaluation, entity resolution, or probabilistic systems.
• A habit of turning uncertainty into testable hypotheses, experiments, and written findings.
• Good judgment about customer-safe failure states, privacy boundaries, security, and proprietary implementation detail.
• A body of work you can explain line by line, including decisions that did not work and what changed afterward.

What does CiteSurge offer?

• Full-time, globally remote work with documented handoffs and agreed collaboration overlap.
• Competitive salary, transparent bands, and equity after one year.
• A four-week summer slowdown and remote-first working practices.
• Meaningful ownership in a small team working on unsolved applied-AI and infrastructure problems.
• Room to publish general technical learning while protecting customer data and proprietary methods.

How do you apply?

Email a short note, your CV or profile, and two examples of systems work you are proud of. Describe one ambiguous or non-deterministic technical problem you investigated and how you determined whether the result was reliable. A concise explanation is more useful than a long cover letter.