AI Engineer - PharmaForce

About PharmaForce

PharmaForce is a leading provider of innovative pharmacy solutions, specializing in 340B Third Party Administration (TPA) and Pharmacy Benefit Management (PBM) services. We leverage cutting-edge technology and industry expertise to help healthcare providers, payers, and patients navigate the complex landscape of pharmacy management.

Our mission is to enhance patient care and access to medications by optimizing pharmacy programs across the spectrum. At PharmaForce, we foster a culture of innovation and collaboration, continuously striving to develop solutions that make healthcare more accessible and affordable for all.

Position Overview

We're hiring a strong Python engineer to join a small, fast-moving team that designs, builds, deploys, and iterates on agentic systems that power both user-facing chat experiences and background automation across our product portfolio.

The Work

• Design and build agentic workflows for chat experiences and asynchronous background

processes

• Choose and apply the right techniques for prompting, tool use, orchestration, memory, and

evaluation

• Write high-quality, production-grade Python

• Iteratively build, test, deploy, and operate services on Azure

• Work closely with a small, fast-moving, fully remote team

The Bar

• Strong Python engineering fundamentals, grounded in a solid computer science foundation:

data structures, control flow, state management, concurrency, and performance trade-offs

• Hands-on experience designing, building, and experimenting with core components of agentic systems—tools, retrieval-augmented generation (RAG), API integrations, sub-agents, orchestration techniques, and graph-based or state machine architectures

• Familiarity with context engineering in agentic workflows, following industry developments, and the ability to learn the art and science as you go

• Working knowledge of FastAPI, Pydantic-AI, Pydantic, Pandas, and Redis or similar libraries,

frameworks, and toolkits

• Skilled at leveraging AI-augmented coding tools (Cursor, Claude Code) as force multipliers— must demonstrate that you're an active orchestrator, reviewer, and iterator, not a passive accepter of outputs

• Experience with observability tools like Logfire for monitoring, debugging, and explaining

outputs

• Understanding of how to evaluate AI outputs—both manual and automated techniques, across different models, and tracking how outputs change over time

• You've built something real that we can look at and talk through—school, personal, or commercial work all count. What matters is that you can clearly explain how you structured things and why you made certain design decisions

• Comfortable operating in ambiguity without heavy process or rigid specs

Nice to Have

• Hands-on experience with Azure or similar cloud infrastructure

• Exposure to non-LLM ML (e.g., regression, classification, time series)

How We Work

• Fully remote

• Guided by Agile Manifesto principles, not ritualized Agile

• Strong bias toward working software, fast feedback, and continuous improvement

• Minimal meetings, high trust, high ownership

• Travel 1–2 times per year

We care far more about your drive and demonstrated knowledge than where you have or haven't been.