We are hiring a Machine Learning Engineer to fine-tune and improve LLMs for healthcare-specific agentic conversations and actions, with an initial focus on revenue cycle management (RCM). You do not need prior RCM expertise — we expect you to learn the domain on the job through close collaboration with product, engineering, operations, and healthcare subject-matter experts.
This role is ideal for someone with hands-on experience fine-tuning open-source LLMs, especially using supervised fine-tuning (SFT) pipelines, and a strong interest in building reliable AI systems for real-world workflows.
Responsibilities:
Build, maintain, and improve supervised fine-tuning pipelines for open-source LLMs.
Fine-tune models for healthcare administrative workflows involving multi-turn conversations, tool use, structured outputs, and task execution.
Develop and refine training datasets from expert examples, workflow traces, synthetic data, user interactions, and model failure cases.
Create evaluation frameworks to measure task completion, instruction following, factual grounding, tool-use accuracy, and regression quality.
Analyze model failures and translate findings into improvements across data, training, prompting, retrieval, tooling, and product behavior.
Collaborate with healthcare and RCM experts to learn workflows and convert domain knowledge into model behavior.
Support production deployment, monitoring, and continuous model improvement.
Hands-on experience fine-tuning open-source LLMs using supervised fine-tuning (SFT) pipelines.
Strong Python and PyTorch skills.
Experience with LLM tooling such as Hugging Face Transformers, PEFT, TRL, Axolotl, DeepSpeed, FSDP, vLLM, or similar frameworks.
Experience preparing, cleaning, labeling, and validating instruction-tuning datasets.
Familiarity with agentic LLM systems, including tool calling, structured generation, retrieval, or workflow execution.
Experience evaluating LLMs using offline benchmarks, human review, regression testing, or production feedback.
Strong debugging skills and the ability to systematically improve model behavior.
Experience with RLHF, RLAIF, DPO, PPO, GRPO, reward modeling, or other preference-optimization methods.
Experience deploying or monitoring LLMs in production.
Experience with synthetic data generation, distillation, LoRA/QLoRA, or distributed training.
Prior exposure to healthcare, fintech, insurance, operations automation, or other high-accuracy domains.
Interest in learning healthcare revenue cycle workflows such as claims, denials, eligibility, prior authorization, and payer follow-up.
You have taken open-source LLMs through fine-tuning, evaluation, and iteration for a real product or workflow. You are comfortable working across modeling, data, infrastructure, and product behavior. You do not need prior healthcare revenue cycle management experience, but you should be motivated to learn the domain deeply and build reliable AI systems for complex operational environments.
Why SuperDial?
Be part of a mission-driven team transforming one of the most broken systems in the U.S.
Work directly with experienced founders and senior operators in AI, healthcare, and automation.
Competitive compensation with equity upside.
Who we are:
SuperDial is transforming AI in healthcare by building scalable, AI-powered solutions that optimize revenue cycle management. Join us and help shape the future of AI in healthcare!
The base salary for this role ranges from $225,000 - $325,000 depending on experience, skill set, and fit. We also offer equity and benefits as part of our total compensation package. Final offers may vary based on experience and qualifications - we’re always open to exceptional talent.
Skills Required
- Hands-on experience fine-tuning open-source LLMs using supervised fine-tuning (SFT) pipelines
- Strong Python and PyTorch skills
- Experience with LLM tooling such as Hugging Face Transformers, PEFT, TRL, Axolotl, DeepSpeed, or similar
- Experience preparing, cleaning, labeling, and validating instruction-tuning datasets
- Familiarity with agentic LLMs, including tool calling and structured generation
- Experience evaluating LLMs using benchmarks and human review
- Strong debugging skills to improve model behavior
What We Do
SuperDial is a voice AI company automating the phone calls that drain time and money from healthcare operations. Its voice AI agents handle benefits verification, prior authorization, claims follow-up, credentialing, and other RCM workstreams, freeing up revenue cycle teams to focus on what matters. Customers include leading provider organizations, billing companies, and payers.
