Promptly is building the first patient-centered global evidence network, offering real world data sharing and monetization capabilities. Together with a selected network of Partners, we generate new knowledge from harmonized datasets, augmented with the collection of longitudinal patient-reported data and patient-generated digital biomarkers within a secure and privacy-preserving environment.

We answer the question – is this patient treatment the best it could possibly be?

What’s Our Purpose

We exist to empower every patient and every health organization on the planet with evidence on the outcomes of care!

Why do we get up in the morning? Well, most healthcare professionals have chosen to work in healthcare driven by their desire to make a difference in patients’ lives. And so have we! We have chosen to follow this calling by addressing the biggest problem in healthcare: the lack of real-world evidence on the outcomes of care.

For us, society denying patients better care due to lack of access to data is unethical, in a world where technology improved so many aspects of our world. Making the right evidence available to healthcare organizations to help prevent one lost life, one care complication, one failed treatment is the moral obligation that big tech companies have – it’s our Hippocratic Oath.

At Promptly, everything we do is driven by our core purpose: to promote better healthcare at lower costs for patients every day, by making health outcomes available.

About The Role

This role is focused on building internal AI products, automations, and agentic workflows that increase operational efficiency across the company.

You will work closely with different departments to identify repetitive work, fragmented processes, manual coordination, and knowledge bottlenecks — and turn them into reliable AI-powered systems.

This is not a research role and not only about calling LLM APIs or building demos. We are looking for someone who can take AI capabilities and turn them into production-grade internal tools that people actually use and trust.

You should be comfortable working across software engineering, workflows, integrations, product thinking, automation, evaluation, and human-in-the-loop systems.

Examples of projects may include: AI copilots for internal teams, automated reporting and operational workflows, AI-assisted sales and customer operations, internal knowledge and search systems, HR and recruiting workflow automation, finance and operations assistants, AI-enabled document processing and approvals, multi-step agentic workflows connected to company systems, and AI tooling to improve how engineers build and ship software.

What You'll Do

1. Design, build, and operate AI-enabled product capabilities across Promptly's platform.
2. Build LLM-powered workflows, agents, retrieval systems, evaluation pipelines, and automation that solve real healthcare and operational problems.
3. Work with product, engineering, data, clinical, and customer-facing teams to translate ambiguous needs into working AI systems.
4. Integrate AI capabilities with existing product surfaces, backend services, data pipelines, APIs, and internal tools.
5. Build evaluation and feedback loops to measure quality, reliability, latency, safety, cost, and user impact.
6. Improve context engineering for AI systems, including retrieval, tool use, structured data access, workflow state, and domain-specific instructions.
7. Design guardrails, review points, and human-in-the-loop workflows for sensitive or high-impact use cases.
8. Help define practical standards for production AI at Promptly: testing, monitoring, observability, debugging, prompt/version management, and rollout practices.
9. Use AI coding agents and development tools to accelerate engineering work while preserving code quality and production ownership.
10. Stay close to the AI development ecosystem, evaluate new tools critically, and help Promptly adopt what creates real leverage.

How We Build With AI

At Promptly, AI-assisted development is part of how we work. We expect engineers to use coding agents, copilots, code search, AI-assisted debugging, and automated review to move faster through real engineering work.

We expect engineers to use AI as part of a modern development workflow, with the same standards of craft, quality, and accountability we apply to any production system. Strong engineers know where AI accelerates the work, where it introduces risk, and where human judgment needs to lead.

You own what you ship. You should be able to explain the design, inspect the diff, validate the behavior, check the security and privacy implications, debug failures, and operate the system in production. If you cannot understand it, test it, secure it, and maintain it, you should not merge it.

Required

What we're looking for

1. 4+ years of software engineering experience, with meaningful experience building and operating production systems.
2. Strong programming fundamentals. You can design, write, review, and debug production-quality code in Python, TypeScript/JavaScript, or comparable modern stacks.
3. Hands-on experience building with LLMs or AI systems in practical applications, not only notebooks or demos.
4. Strong fluency with AI-assisted development. You use coding agents and AI tools as part of your normal engineering workflow, including codebase exploration, implementation, refactoring, test generation, debugging, documentation, and review.
5. Good judgment when working with AI-generated code. You inspect generated diffs, validate assumptions, write meaningful tests, reject weak suggestions, and take ownership of the final implementation.
6. Practical understanding of LLM application patterns such as prompting, retrieval, tool use, structured outputs, workflow orchestration, agents, evaluation, and observability.
7. Experience designing systems around model behavior, including reliability, latency, cost, failure modes, fallback paths, and user experience.
8. Ability to build evaluation loops for AI systems. You can define what good looks like, create test sets or review workflows, measure behavior, and improve quality over time.
9. Strong product judgment. You can connect AI capabilities to user value, customer needs, and business outcomes instead of building technology for its own sake.
10. High agency in ambiguous environments. You can create clarity, make trade-offs, and move work forward without needing every detail defined upfront.
11. Strong communication skills. You can explain model behavior, system design, risks, and trade-offs to engineers, product managers, customer-facing teams, and leadership.

Preferred

1. Experience in healthcare, health technology, life sciences, clinical data, real-world evidence, or another regulated enterprise domain.
2. Experience building AI systems over complex data, including structured data, documents, clinical or operational workflows, analytics, or data-intensive products.
3. Experience with agentic workflows, tool-calling systems, MCP-style integrations, workflow engines, or multi-step automation.
4. Experience with RAG systems, embeddings, reranking, chunking strategies, knowledge bases, or semantic search.
5. Experience with evaluation frameworks, LLM-as-judge patterns, golden datasets, human review workflows, regression testing, or AI observability.
6. Experience with cloud platforms such as AWS, GCP, or Azure.
7. Experience with backend systems, APIs, queues, event-driven systems, data pipelines, or distributed processing.
8. Familiarity with security, privacy, compliance, and enterprise IT constraints.
9. Experience shaping AI-assisted engineering practices for a team.
10. Ability to read AI research or technical papers and translate useful ideas into pragmatic product or platform improvements.

You'll be a strong fit if

1. You care about product usefulness more than model novelty.
2. You can explain where an AI system is likely to fail and how you would measure it.
3. You know when to use AI and when simpler software is the better answer.
4. You are comfortable working with incomplete information and making progress through careful iteration.
5. You care about craft, tests, observability, security, privacy, and production behavior.
6. You are not impressed by generated code or generated answers just because they look polished.
7. You want to build AI systems that matter in healthcare, not AI demos that only work in a controlled environment.
8. 
   

Position

1. Remote-first
2. Full-time

What We Offer

Ownership & Growth

1. Define and own a strategic global initiative from the ground up
2. Shape the future of Promptly’s partner ecosystem and data network expansion

Financial Benefits

1. Competitive salary
2. Annual performance bonus
3. Equity compensation via our ESOP (open to all team members)
4. Annual training allowance
5. Private health insurance
6. Home-office equipment allowance

Non-Financial Benefits

1. Equal opportunity and inclusive environment
2. Flexible work schedule and vacation policy
3. Corporate events and international team gatherings

What Is The Recruiting Process Like

1. Initial Interview — Meet your future manager and/or team members to get to know each other and understand the scope of the role.
2. Technical & Strategic Assessment — Work on a short case related to partner management or program design.
3. Final Interview (if needed) — Deep-dive discussion to align on expectations and vision.
4. Offer Stage — We’ll share the offer and welcome you to the team!
5. 
   

Our Culture & Values

Empathy — Ownership — Responsibility — Teamwork — Excellence

If you embrace these values, you will thrive at Promptly. We are a purpose-driven company where everyone acts as an owner, committed to improving healthcare through data, technology, and collaboration.

Are you looking for remote jobs near your area? At Yulys, thousands of employers are looking for exceptional talent like yours. Find a perfect job now.