Implementation Engineer

About Phluence

Phluence builds AI agents for the pharmaceutical industry. They handle the work that helps patients start and stay on their therapy: enrollment, benefits verification, pharmacy coordination, follow-up, and more, across voice, text, and digital channels. Most of our clients are pharmaceutical manufacturers, and we also work with clinics and hospitals.

About the position

Implementation Engineers are the people who turn our platform into live programs. You'll work closely with Solutions Consultants, Product Managers, Project Managers, and Platform Engineers to design, build, test, and launch solutions that patients and providers use every day.

As an Implementation Engineer, you will:

• Be part of a collaborative team creating compelling patient experiences for our healthcare clients
• Build and launch AI agents for patient support and market access programs
• Build voice agents on VAPI connected to our own LLM backend: conversation flows, prompts, tool calls, handoff to human agents, and the testing that proves they work
• Use Phluence's Domain Specific Languages (DSLs), our core building blocks, along with JavaScript/TypeScript and Python, to build workflow orchestration, data ingestion, integrations, and automated tests
• Use LLMs to process and analyze healthcare data, for example running data models that predict whether a patient's insurance will cover a drug
• Deploy, monitor, and troubleshoot solutions on AWS
• Use AI tools like Codex, Claude, and Gemini every day to build, test, and document faster
• Develop a deep understanding of the patient journey and pharmaceutical workflows
• Bring a technical perspective to solution and UX design discussions
• Troubleshoot production issues, including on-call support during working hours
• Contribute to the platform core when a project needs something that doesn't exist yet

Who will thrive as an Implementation Engineer?

You own your work from start to finish. When you ship something, you've made sure it's accurate, tested, and on time, because there's a patient or a client on the other side of it. Priorities here can shift quickly, and you keep work moving without waiting for step-by-step direction.

You're curious about AI and already use it to get real work done. You know where LLMs shine, where they fail, and how to test an agent before trusting it with a patient conversation. When a new model or tool comes out, you want to try it, and you can tell whether it actually helps.

You enjoy solving customer problems with technology and working on a small, collaborative, and highly productive team. You're a strong analytical thinker, you balance competing priorities well, and you stay calm under pressure.

Required skill set

• An undergraduate degree in a STEM field, or equivalent work experience
• Strong spoken and written English; you'll work with US-based clients and teammates every day
• 2+ years of professional experience with JavaScript/TypeScript or Python
• Daily use of AI coding assistants such as Codex, Claude, or Gemini
• Experience with AWS, especially Lambda, S3, SQS, DynamoDB, CloudWatch, and Systems Manager Parameter Store
• Strong SQL and relational database skills (PostgreSQL or Redshift)
• Comfortable with the Linux command line, Git, and CI/CD workflows
• Able to break down unclear problems into actionable work, manage expectations, and say clearly what you need to succeed
• Strong communication skills and an ability to build trust with clients and teammates
• An ability to deliver what people need, not just what they ask for
• Evidence of a capacity for exceptional performance (e.g., a degree from a top-tier university or program, or entrepreneurial experience)

Other valuable skills

• Hands-on experience building with LLMs: prompt design, tool or function calling, structured outputs, and evaluating results
• Experience building voice or conversational AI agents (VAPI or similar platforms, speech-to-text, text-to-speech)
• Agent frameworks, RAG, vector databases, or tools for evaluating and monitoring LLM output
• Data engineering or analytics: data pipelines, data modeling, BI tools
• Classic machine learning or NLP: training data, features, models, and preprocessing

What we offer

We offer competitive compensation, which we'll go over with you during the interview process, and fully remote work from anywhere in Mexico (Guadalajara preferred). You'll also have real room to grow: you'll take on more ownership, work across new products and technologies, and expand your skills.

Diversity & Inclusion

Phluence believes that a team with a diversity of backgrounds, perspectives, and skills brings better ideas to the table. We also know that supporting a diverse team takes ongoing effort, and we work hard to create an environment where everyone on the team can thrive.