Job Specifications
About Nabla
We are a team of entrepreneurs, clinicians and engineers committed to bringing back joy to the practice of medicine.
Together with a community of clinician innovators, we’ve harnessed the best of machine learning science to develop Nabla: the leading AI assistant that’s restoring the human connection at the heart of healthcare. By streamlining clinical documentation, Nabla is helping clinicians focus on what matters most - patient care. Today, over 85,000 clinicians across 130+ healthcare organizations trust Nabla to support how they deliver care every day.
We’re at the start of an ambitious journey: Ambient listening, dictation, coding, and command capabilities are all converging into a proactive assistant that intuitively streamlines clinical and financial workflows.
Backed by a recent $70M Series C, we’re hiring to build the next generation of clinical AI and improve the lives of clinicians and patients everywhere.
This is a great time to join us!
The Prompt Engineering Role
At Nabla, we think about AI systems as products — and prompts as first-class infrastructure.
Modern LLM-powered systems don’t fail because of missing models, but because of vague instructions, leaky evaluation, and poorly specified success criteria. Prompt engineering is the discipline that makes these systems reliable, debuggable, and safe — especially in clinical contexts.
We are looking for our first Prompt Engineer to own the quality layer of our LLM systems. You will work closely with Product, ML, and Clinical teams to design, iterate, and rigorously evaluate prompts that power our clinical note generation and our internal “judge AI” used to assess output quality (hallucinations, recall, style, clinical correctness).
This role is ideal for someone who genuinely enjoys the craft of prompt design, evaluation, and iteration — and who brings rigor, patience, and taste to work that others often find tedious but mission-critical.
This role will likely start as freelance, with the possibility to expand over time.
Product at Nabla
The product team is a tight-knit group of builders, designers, and strategists. Together with engineering, we define and deliver high-impact tools that delight clinicians and solve their most pressing problems.
Our AI systems are at the core of the product experience. Ensuring they are accurate, reliable, and clinically safe is not optional — it is foundational to trust and adoption.
Responsibilities
Prompt design & iteration
Design, write, and maintain high-quality prompts for:
Clinical note generation
Evaluation / “judge” models assessing hallucinations, recall, structure, tone, and adherence to clinical standards
Systematically iterate on prompts based on failure modes, edge cases, and real-world usage.
LLM evaluation & quality
Define clear, measurable quality criteria for each type of output, including accuracy, completeness, style, and clinical relevance.
Build and maintain prompt-based evaluation frameworks to consistently score and compare outputs across models and prompt versions.
Identify blind spots, regressions, and trade-offs in model behavior.
Reliability & rigor
Treat prompts as production artifacts:
Versioned
Documented
Tested against known failure cases
Create reusable prompt patterns and guidelines to ensure consistency and maintainability.
Cross-functional collaboration
Work closely with ML engineers to surface model limitations and propose prompt-level mitigations.
Partner with Product and Clinical teams to translate qualitative expectations into explicit, testable instructions.
Act as a bridge between “what clinicians expect” and “what LLMs actually do.”
Your DNA
Prior hands-on experience with prompt engineering for production LLM systems (not just experimentation or demos).
Strong written communication skills and an exceptional attention to detail.
A rigorous mindset: you enjoy defining criteria, edge cases, and evaluation frameworks.
Comfort working with:
LLM APIs (OpenAI, Anthropic, Gemini, etc.)
Structured prompt formats (system / developer / user messages)
Basic scripting or tooling to run prompt tests (Python, notebooks, or similar)
High tolerance — and even enjoyment — for iterative, detail-oriented work that requires patience and taste.
Ability to reason about hallucinations, recall failures, ambiguity, and instruction-following limitations.
Interest in healthcare, clinical workflows, or safety-critical AI systems is a strong plus.
Autonomous and self-directed; comfortable operating with minimal process in a fast-moving startup environment.
Where We are based
Our offices are based in Paris 3e (Arts & Métiers).
Remote policy: 1 day a week (with some flexibility). Possibility of working remotely 1-2 weeks once a year.
Benefits
Just like we’re dedicated to supporting doctors’ well-being, ensuring yours is a top priority. We firmly believe that by prioritizing your well-being, we support you to excel in your work.
Public transportation costs co