Senior Software Engineer, AI - UpDoc

Rocket Lab; United States; Remote; USD 120,000 - 160,000; Full time

Job summary

Rocket Lab is seeking a talented senior engineer to join their team in a fully remote role. You will lead the development of a patient-facing conversational agent and implement systems for effective voice and multimodal conversations, leveraging your expertise in LLM applications and modern backend development.

Benefits

Competitive compensation

Equity in an early-stage startup

Cutting-edge LLM tools

Qualifications

• 5+ years of professional software development experience.
• 2+ years of experience with backend web development.
• Experienced with type-hinted, modern Python.

Responsibilities

• Lead the development of UpDoc's patient-facing conversational agent.
• Implement scalable, low-latency systems for voice/multimodal conversations.
• Collaborate with clinical experts to validate performance.

Skills

Python

LLM applications

backend web development

MLOps best practices

cloud platforms

containerization technologies

Job description

About UpDoc

At UpDoc, we are building the world's first clinically validated, physician-supervised conversational agent that manages chronic diseases; the first step towards a true "AI doctor". With partners including Stanford, Mayo Clinic, Eli Lilly, UCSF Health, and Microsoft, UpDoc is working to build a future where all patients can access high-quality, high-touch care. Learn more about us here.

We are seeking a talented and motivated senior engineer to join our team. You will primarily work on UpDoc’s patient-facing conversational agent. This is a fully remote position.

Who You Are

You’re an experienced senior engineer with a backend tilt. You’re well-versed in all things web and have experience building LLM applications end-to-end, even if not in a professional context. You follow the AI/LLM space closely, play with new technologies as they come out, and are excited to use these technologies to build safe, reliable medical AI systems.

What You'll Do

• Lead the development of our patient-facing conversational agent

• Implement a scalable, low-latency system for voice/multimodal conversations

• Implement rigorous prompt engineering processes and develop useful metrics for system evaluation

• Identify where fine-tuning and alignment might be valuable, and create data pipelines to enable fast experimentation

• Work with other backend engineers to deploy AI models and chat/voice APIs

• Help identify, evaluate, and implement emerging LLM technologies, tools and frameworks

• Collaborate with clinical experts to validate performance and medical accuracy

• Work on developing backend services using FastAPI and Pydantic

What You’ll Need

• 5+ years of professional software development experience, including 2+ years of experience with backend web development

• Experienced and comfortable working with type-hinted, modern Python

• 2+ years of experience building end-to-end LLM applications, personally or professionally

  • Experience integrating/optimizing LLMs in production environments

  • Knowledge of evaluation frameworks

  • Knowledge and experience with MLOps/LLMOps best practices

  • Experience building AI infrastructure from 0 -> 1

• Experience with cloud platforms (especially Azure) and containerization technologies

Highly Desired

• Professional experience building end-to-end LLM-powered applications

• Experience with model fine-tuning/alignment

• Experience in an early stage startup environment

• Experience with healthcare industry standards, such as FHIR, and regulations, including HIPAA and SOC 2

Why You Should Join Us

• Join a small, high-impact team building the future of healthcare

• Work with cutting-edge LLM tools that support world-class medical institutions

• Shape core technical architecture in an emerging field

• Competitive compensation and equity in an early-stage startup

Interview Process

1. Application form

2. Conversation with our CTO

3. Technical interviews:

   1. Coding interview focused on a real-world application relevant to the role (e.g., LLMs, backend engineering)

   2. Architecture/whiteboarding interview focused on discussing general application-design relevant to the role

4. Conversation with our CEO