About Verc

Verc is building an AI-native operating system for loan servicing and collections. Our mission is to modernize one of the most complex, regulated, and human-critical industries by replacing fragmented legacy workflows with intelligent, secure AI systems built for production.

We power real-time decision-making, compliance-aware automation, and agent-assisted workflows across voice, text, and structured data. Our platform combines multi-agent LLM systems, speech technologies, predictive models, deterministic logic, and structured data pipelines to support high-stakes financial operations while maintaining trust, transparency, and regulatory rigor.

Verc is built from the ground up as a multi-tenant, cloud-native platform with deep attention to security, auditability, guardrails, and data isolation. Our customers rely on us for mission-critical operations where correctness, reliability, and explainability are non-negotiable.

Role Overview:

We are looking for an AI Product Engineer who can own AI-powered features end to end, from idea and specification through implementation, evaluation, and production reliability.

This role sits at the intersection of product thinking, design thinking and AI systems engineering. You will work directly with founders. You will deeply understand customer workflows and translate them into creative, analytically grounded AI solutions. These solutions may range from multi-agent orchestration and retrieval pipelines to predictive models, guardrail logic, or product and dashboard design decisions. You will consistently choose the appropriate level of complexity for a regulated, high-stakes environment.

You will translate operational requirements and compliance constraints into structured AI behavior, measurable outcomes, and reliable customer-facing workflows.

What You'll Do

Act as a forward-deployed builder, partnering closely with customers to uncover workflow pain points, ship AI-driven solutions into live environments, ship code early and often, and iterate rapidly based on real usage signals and measurable outcomes
Own product features end-to-end from ideation through to building responsive, user-centric web apps and backend generative AI services and APIs
Turning complex backend capabilities into simple, elegant product experiences
Work directly with founders to develop and ship products with a user-centric approach.
Design and implement multi-agent LLM systems with structured orchestration, tool use, memory, and domain-specific constraints
Build and refine embedding, retrieval, and predictive pipelines that ground AI behavior in structured and unstructured data
Implement guardrails, policy enforcement logic, and evaluation criteria to ensure regulatory alignment and safe system behavior
Iteratively improve prompts, agent configurations, and workflow logic to increase task success, reduce hallucinations, and ensure policy adherence
Define and track success metrics across product performance, reliability, latency, and cost
Work across backend services, APIs, and event-driven workflows to ensure AI systems are integrated, observable, and production-ready
Monitor live systems, investigate edge cases, and continuously harden production behavior
Leverage modern AI tools, including coding assistants and research systems, thoughtfully and responsibly to accelerate development while maintaining correctness, security, and compliance standards

You might be a good fit if you have:

Bachelor’s or Master’s degree in Computer Science, Engineering, Applied Mathematics, Statistics, AI/ML, Economics, or a related technical field
Strong proficiency in Python and comfort working across backend systems and APIs
Deep appreciation for intuitive user experiences
Ability ship quickly, but with strong taste and craftsmanship
Deep understanding of LLM systems, agent architectures, retrieval pipelines, evaluation methods, conventional ML approaches, and voice AI systems, including speech-to-text, text-to-speech, and real-time conversational workflows
Proven experience shipping and operating AI or ML systems in production environments where reliability and correctness matter.
Ability to reason about model tradeoffs, system constraints, and user impact simultaneously
Strong analytical thinking and ability to turn ambiguous requirements into structured, measurable systems
Demonstrated ability to make pragmatic tradeoffs between speed, correctness, safety, and long-term maintainability.
Clear communication skills and comfort working cross-functionally in a fast-paced startup environment
High ownership mindset, proactive, fast-moving, and highly accountable, can take a one-sentence idea and independently turn it into a working product.
Curiosity about building safe, explainable AI in regulated environments