Senior Software Engineer, Artificial Intelligence

Socket.dev; United States; On-site; USD 150,000 - 175,000; Full time

Benefits offered by this job

Medical benefits

Unlimited PTO

401(k) plan

Stock options

Bonuses

Job summary

Socket.dev is seeking a Senior Engineer, AI, to lead the development of language and voice technologies for healthcare interactions. You will drive LLM applications (RAG, classification, fine-tuning) and NLP/ML components, delivering production-ready AI across voice and digital channels.

You will prototype and productionize ML features in Python, build APIs, partner with product and medical teams to implement safeguards, monitor performance, and deploy services in AWS/Kubernetes, staying at the

Qualifications

• 5+ years of software engineering or applied ML experience.

Responsibilities

• Design, build, and optimize LLM applications (RAG, classification, summarization).
• Prototype and productionize ML/AI features in Python and integrate with backend services.
• Collaborate with product/medical teams to implement safeguards for AI outputs.
• Develop APIs for LLM applications used by other components.
• Create automated evaluations to measure LLM performance.
• Deploy AI services end-to-end in AWS/Kubernetes.
• Research and test new AI tools and architectures.
• Contribute to conversational AI strategy for healthcare applications.

Skills

Python backend

LLMs

Embeddings

NLP

ML frameworks

AWS

Kubernetes

Productionization

Education

Bachelor's degree preferred

Tools

Flask/FastAPI

Hugging Face

OpenAI API

LangChain

LangGraph

Job description

About the Role

We are looking for a Senior Engineer with AI expertise to lead the development of advanced language and voice technologies that transform how patients and providers interact. In this role, you will drive Fabric’s work in large language model (LLM) applications—such as retrieval-augmented generation (RAG), classification, and fine-tuning—as well as speech, natural language processing (NLP), and machine learning (ML). This is a hands-on, high-impact position at the intersection of innovation and production engineering. You will work cross-functionally to build intelligent, responsive dialogue systems and infrastructure for Fabric’s conversational AI experiences across voice and digital channels.

What You’ll Do

As a Senior Engineer, AI, you will be instrumental in bringing advanced AI concepts from prototype to production. Your primary responsibilities will include:

• Designing, building, and optimizing LLM applications (e.g., RAG, classification, summarization).
• Prototyping and productionizing ML and AI features in Python, integrating them with backend services.
• Partnering with product and medical teams to develop appropriate safeguards and business constraints for AI outputs.
• Collaborating with engineering to develop APIs for LLM applications used by other product components.
• Creating automated evaluations to measure the accuracy and performance of LLM-powered systems.
• Maintaining and improving existing NLP and AI diagnosis production components.
• Developing analytics to monitor system performance and prioritize improvements.
• Deploying AI services end-to-end in cloud-native environments using AWS and Kubernetes.
• Staying on the cutting edge by researching and testing new AI tools, APIs, and architectures.
• Contributing to our conversational AI strategy and helping shape the future of healthcare AI.

Why You Might Be a Good Fit

• You care deeply about the mission: You are passionate about deploying technology that empowers patients to engage with healthcare in their preferred language and format.
• You're an autonomous problem solver: You excel at breaking down complex problems in the AI space and finding effective solutions, operating with autonomy and ownership.
• You’re a leader in your field: You stay current on machine learning, foundation models, and algorithms related to text and text-to-speech technologies.
• You value robust and responsible AI: You're committed to building robust testing and monitoring pipelines that provide insight into real-time performance, and you are dedicated to developing safeguards for responsible AI use.
• You thrive on collaboration: You enjoy working cross-functionally across teams, integrating AI use cases into products by understanding their APIs and data systems.
• You're a clear communicator: You're skilled at communicating complex ideas clearly to both technical and non-technical audiences.

This Might Not Be The Right Fit If…

• You prefer a role that is focused purely on research rather than hands-on, production-level engineering and deployment.
• You are not comfortable with the ambiguity and fast-paced nature of developing cutting-edge AI systems from the ground up.
• You prefer to work in a silo rather than collaborating closely with product, medical, and other engineering teams.
• You are not passionate about the specific application of AI to solve real-world problems in the healthcare industry.

Your Qualifications

• A bachelor's degree in a related field is preferred, but not required.
• 5+ years of experience in software engineering or applied machine learning, with a strong focus on building real-world AI/ML systems.
• Proficiency in backend development using Python (Flask or FastAPI), and 3+ years of hands-on experience with LLMs and LLM agents.
• Core Competencies:
  • Solid understanding of embeddings and embedding databases.
  • Experience in NLP or speech processing technologies.
  • Familiarity with modern AI/ML frameworks and tools (e.g., Hugging Face, OpenAI API, LangChain, LangGraph).
  • Experience building and deploying cloud-native applications on AWS with Kubernetes and container tools.
  • Demonstrated ability to bring models from research to production, solving for latency, scale, and reliability.
  • Effective communication skills and the ability to work across disciplines in a fast-paced, agile environment.

Bonus Points

• Experience with conversational agents, or real-time voice communication (e.g., WebRTC, telephony), ASR, TTS, or voice assistants.
• Prior work on multimodal AI interfaces or agent-based dialogue systems.
• Experience hosting, scaling, and fine-tuning open-source models.
• A passionate interest in improving healthcare access and outcomes through applied AI.

The national pay range for this role is $150,000.00 - $175,000.00 per year. Actual compensation will be determined by factors such as the candidate's geographic market, experience, skills, and qualifications. Certain roles may also be eligible for additional compensation, including a comprehensive benefits package such as medical, dental, vision, unlimited PTO, and a 401(k) plan, stock options and bonuses. If your compensation requirement is greater than our posted range, please still consider applying; a determination can be made based on unique qualifications. Expected compensation ranges for this role may change over time.