About Sully

Sully.ai is building the AI operating system for healthcare. Our mission is to make doctors superhuman through AI, so every patient can get faster, better, and more accessible care.

Healthcare is one of the most important systems in the world, yet clinicians still lose hours every day to documentation, scheduling, intake, coding, and administrative work. We are changing that with AI medical employees: Scribes, Receptionists, Coders, Consultants and other agents that operate inside real clinical workflows.

We are backed by Amity Ventures, YC, Baidu Ventures amongst others, have raised $40M+, and are already deployed across hundreds of healthcare organizations. Our products process tens of thousands of clinical encounters every day, automate millions of minutes of administrative work, and help clinicians spend more time with patients.

The role

As a Forward Deployed Engineer / Solutions Architect, you will operate between customers, customer success, product, and engineering. Your job is to bridge the gap between our core product and research teams and our customers.

You will help customers adopt Sully's products — across our portfolio of AI medical employees, from Scribe to Receptionist to Coder and beyond — by understanding their workflows, configuring solutions, testing behavior, debugging issues, and translating customer needs back into product and engineering feedback. Our products are configuration-driven: much of the behavior customers experience is composed from prompts, routing logic, workflow rules, integrations, and operational settings rather than bespoke code. You'll be the person who turns a messy clinical workflow into a working, tested deployment.

This is a customer-facing engineering role for someone who enjoys working closely with both customers and builders. You should be comfortable digging into APIs, integrations, AI-agent behavior (including real-time text and voice agents), configuration systems, evals, and debugging — while also being able to explain ideas clearly and build trust in customer conversations.

Just as importantly, you will help us improve the way we deliver for customers. We receive a constant stream of feature and customization requests as customers configure their agents and workflows. A core part of this role is absorbing that stream and deciding, with good judgment, what to configure now, what to turn into a repeatable template or playbook, and what to escalate as a real product gap — and being able to defend those tradeoffs to both customers and engineering. Forward Deployed Engineers are close enough to customers to understand the real operational pain, and technical enough to identify the tools, processes, and product improvements that make future deployments faster, smoother, and more scalable.

What you’ll do

Deploy and configure customer workflows

• Own hands-on setup for customer deployments across Sully's AI products.

• Configure workflows, routing logic, prompts, operational settings, and product behavior.

• Translate customer workflows into deployable configurations.

• For voice and scheduling products specifically: configure agent behavior, transfer/handoff logic, voicemail handling, and clinical scheduling rules against customer EHRs.

• Test workflows end-to-end before and after launch.

• Identify gaps between customer needs and current product capabilities.

Support technical onboarding and implementation

• Help map customer systems, workflows, data flows, and integration requirements.

• Partner with engineering and implementation teams on testing, validation, and rollout.

• Investigate technical issues during onboarding and deployment.

• Create repeatable deployment playbooks and documentation.

• Help customers get live faster without sacrificing quality or safety.

Work directly with customers

• Join customer calls when technical clarification is needed.

• Ask structured questions to understand workflows, edge cases, and constraints.

• Explain technical tradeoffs clearly to non-technical stakeholders.

• Build trust with customer teams by being precise, responsive, and honest.

• Know when to solve, when to configure, and when to escalate.

Improve AI-agent quality and reliability

• Test and evaluate deployed AI workflows using transcripts, traces, evals, and live testing tools.

• Debug configuration issues, product gaps, and unexpected agent behavior — for voice agents this includes recognition, latency, interruptions, transfers, and scheduling logic.

• Partner with AI and engineering teams when deeper investigation is needed.

• Help define safe and repeatable deployment practices for configurable AI systems handling sensitive patient data.

• Surface recurring issues that should become product improvements.

Feed product signal back to engineering

• Identify patterns across customer requests.

• Document recurring pain points and missing capabilities.

• Recommend which repeated customizations should become product features, templates, or tooling.

• Help engineering understand customer reality without pulling engineers into every customer conversation.

What good looks like

• Customers onboard and configure Sully products faster, with fewer handoffs and less manual effort — measurably reducing time-to-live for new deployments.

• Customer issues and technical requests are resolved faster because there is a strong technical partner close to the customer.

• Deployed AI workflows perform reliably in production (e.g. higher task-completion / success rates on launched workflows), and are tested, documented, and easy to repeat across customers.

• Manual work in agent configuration, workflow setup, and customer technical operations is identified, reduced, and turned into better tools, templates, or processes.

• Repeated customer needs are pulled into a tight feedback loop with product and engineering, and engineering time spent in customer calls goes down.

• Customer-facing teams have a technical counterpart who can translate customer reality into clear product and engineering signal.

• The role improves both the customer experience and the internal operating model for scalable product configuration.

What we’re looking for

Required

• Experience in software engineering, solutions engineering, forward deployed engineering, implementation engineering, technical consulting, or a similar technical role.

• Hands-on experience working with AI products, AI agents, LLM workflows, prompt/configuration systems, evals, or similar agentic systems.

• Ability to read code (we work primarily in TypeScript and Python), write SQL to investigate issues, understand APIs and integrations, and reason through technical workflows.

• Strong written communication and documentation habits.

• Ability to translate messy customer workflows into structured technical requirements.

• High ownership and bias toward action.

• Comfort working directly with customers, including clinical and non-technical stakeholders.

Strong signals

• Experience with AI agents, LLM workflows, prompt/configuration systems, evals, or automation tools.

• Experience with healthcare technology, EHRs, or clinical integrations (e.g. Athena, AdvancedMD, FHIR/HL7) and awareness of HIPAA/PHI handling.

• Startup or founder experience, and comfort operating in 0→1, high-ambiguity environments.

• Experience using AI-native development tools to move quickly.

• Strong debugging instincts and customer empathy.

Who this role is not for

This role may not be a fit if you:

• Want to work only on core product engineering.

• Avoid customer conversations.

• Need fully specified tickets before taking action.

• Are uncomfortable with ambiguity.

• Need a stable, fully-documented product — our products move fast and you'll help build the playbooks and rough edges as you go.

• Treat every customer request as something engineering must build.

• Over-promise to avoid difficult conversations.

Interview process

• Introductory conversation

• Technical screen or systems walkthrough

• Customer workflow exercise

• AI-agent or deployment quality discussion

• Final cross-functional interview