Senior AI Engineer

Ellipsis Health
San Francisco, CA
Hybrid

Who this role is best for

Candidates with experience in agentic systems and healthcare will find this senior engineering role in San Francisco, focused on deploying pre-trained AI models into clinical applications, highly suitable.

Best fit for

  • Candidates with experience in agentic systems and healthcare will find this senior engineering role in San Francisco, focused on deploying pre-trained AI models into clinical applications, highly suitable.
    — “building complete, production-ready applications around pre-trained AI models”
  • Individuals with a track record of deploying complex LLM-powered systems in regulated environments will align well with this role.
    — “high-acuity, deeply regulated technical integrations”
  • Candidates who have mentored engineers and led design reviews will be well-positioned for this role's emphasis on technical rigor.
    — “Foster a culture of technical rigor by setting high coding standards, leading design reviews”

Things to consider

  • A strong background in healthcare or similar regulated domains is likely expected due to the clinical nature of the applications.
    — “ensure AI platforms operate safely and ground outputs in validated healthcare protocols”

How to stand out

  • Highlight experience with multi-agent orchestrations and LLM deployment in your resume and interview responses.
    — “architecting, implementing, and deploying complex LLM-powered applications”
  • Demonstrate your ability to build scalable systems with examples of high-fidelity tool utilization.
    — “multi-step reasoning, dynamic memory allocation, long-context evaluation”
  • Showcase your work with automated data curation pipelines and their impact on product quality.
    — “automated data curation pipelines to extract, filter, and structure user feedback signals”
  • Emphasize your experience with quantitative evaluation frameworks and statistical tracking of AI performance.
    — “multi-dimensional quantitative evaluation frameworks and continuous testing infrastructure”
  • Demonstrate your ability to collaborate with clinical experts and product teams in complex, matrixed organizations.
    — “highly matrixed, collaborative organization alongside clinical experts”
Pace · Fast PacedCollaboration · HighAutonomy · MediumDecision Impact · Company

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • design scalable agentic systems
  • deploy production-ready applications
  • implement evaluation frameworks
  • develop data curation pipelines
  • collaborate with clinical experts
Typical background
AI engineeringLLM deployment

Skills & requirements

Required

AI Application ArchitectureLLM DeploymentAgentic SystemsProduction DeliveryEvaluation And BenchmarkingData PipelinesCross-functional CollaborationEngineering Excellence

Preferred

Technical LeadershipComplex Technical Integrations

Stack & domain

Ai/mlConversational AIVoice Biomarker TechnologyLlmsAgentic SystemsProduction-ready ApplicationsPrompt OptimizationEvaluation FrameworksLlm-as-a-judge RubricsStatistical TrackingData Curation PipelinesUser Feedback SignalsExecution LogsExpert LabelsHigh-quality DatasetsClinical ExpertsProduct ManagersSoftware EngineersAI PlatformsValidated Healthcare ProtocolsCoding StandardsDesign ReviewsToolingMentoringPythonMachine LearningDeep Learning FrameworksAdvanced Data StructuresAlgorithmsDistributed SystemsScalable InfrastructureTechnical LeadershipComplex Technical Project WorkstreamsOrganizational Engineering DirectionsTechnical TalentHealthcareFintechAerospaceLeadershipCommunicationTeamworkProblem-solvingAttention To DetailAnalytical ThinkingAIMLClinical Applications

About the role

Original posting from Ellipsis Health via Ashby

Ellipsis Health is creating cutting-edge AI/ML products that solve healthcare staffing challenges and administrative burdens using conversational AI and our patented voice biomarker technology, helping deliver better healthcare for everyone. We are headquartered in Silicon Valley and are funded and supported by some of the most preeminent venture capital teams.

In this role, you will be a core contributor within our AI Research & Engineering team, building complete, production-ready applications around pre-trained AI models rather than training foundational models from scratch. You will drive the architecture and deployment of frontier agentic systems and collaborate directly with core infrastructure and platform teams to turn advances in LLMs and agentic AI into robust, secure, and low-latency clinical applications.

Responsibilities:

Agentic Application Architecture: Design, build, and optimize scalable systems and orchestration pipelines capable of multi-step reasoning, dynamic memory allocation, long-context evaluation, and high-fidelity tool utilization.

Production Delivery: Build production-ready applications around pre-trained models, taking prototypes through to production scale. Implement and adapt state-of-the-art techniques such as automated prompt optimization.

Evaluation & Benchmarking: Architect and maintain multi-dimensional quantitative evaluation frameworks and continuous testing infrastructure. Implement LLM-as-a-judge rubrics and statistical tracking to evaluate agent capabilities and guarantee zero-regression product updates.

Data Pipelines: Develop and scale automated data curation pipelines to extract, filter, and structure user feedback signals, execution logs, and expert labels into high-quality datasets.

Cross-Functional & Clinical Collaboration: Work closely within a highly matrixed, collaborative organization alongside clinical experts, product managers, and software engineers to ensure AI platforms operate safely and ground outputs in validated healthcare protocols.

Mentorship & Engineering Excellence: Foster a culture of technical rigor by setting high coding standards, leading design reviews, standardizing tooling, and mentoring other engineers across the team.

Minimum Qualifications:

  • Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.
  • 5+ years of practical software development experience with a heavy emphasis on product design, core system architecture, and shipping scalable software platforms.
  • Advanced programming proficiency in Python.
  • Proven track record of architecting, implementing, and deploying complex LLM-powered applications, multi-agent orchestrations, or autonomous systems in a production environment.

Preferred Qualifications:

  • Master’s degree in Computer Science, Artificial Intelligence, or a related technical field.
  • Hands-on experience with machine learning or deep learning frameworks (e.g., PyTorch, JAX, or TensorFlow).
  • Experience with advanced data structures, algorithms, distributed systems, and scalable infrastructure.
  • 3+ years of technical leadership experience, including leading complex technical project workstreams, defining organizational engineering directions, or directly mentoring technical talent.
  • Experience working within complex, highly collaborative matrixed organizations on high-acuity, deeply regulated technical integrations (e.g., healthcare, fintech, or aerospace).

Salary and Benefits:

We offer competitive salary and benefits, including 401(k) matching, health, vision, and dental insurance, and very flexible paid time off.

The typical salary range for this role is $160,000 to $210,000 USD, depending on skills, qualifications, and relevant experience.

Background Checks:

As a health technology company, we reserve the right to run background checks on candidates to whom we extend offers, in compliance with applicable laws. We evaluate candidates holistically and comply with all “ban the box” regulations.

Assistance:

If you have a disability or require accommodations during the application or recruitment process, please contact careers@ellipsishealth.com.

Source: Ellipsis Health careers (Ashby)

Similar roles

More roles at Ellipsis Health