Senior Software Engineer, AI

Overview

Location: Remote (U.S. based)

Employment Type: Full-time

About Verantos

Verantos (https://verantos.com) is a market leader in high-accuracy real-world evidence (RWE) generation. The Verantos RWE platform integrates heterogeneous real-world data sources and generates evidence with the accuracy necessary for regulatory and reimbursement use. The Verantos RWE platform leverages data science and artificial intelligence, along with advanced data sources such as electronic health records (EHR), to generate RWE capable of supporting complex clinical studies. Some of the largest biopharma companies in the world are Verantos customers.

We use a heterogeneous tech stack on AWS with data processing, artificial intelligence, workflow, and analytic components.

Role Overview

We’re seeking a Senior Software Engineer, AI to join our multidisciplinary product team and drive the design and delivery of intelligent systems that support regulatory-grade clinical studies. You’ll contribute to a cross-functional group of designers, product managers, QA, fullstack developers, and DevOps engineers, helping to integrate agentic, RAG-based AI systems into real-world clinical tooling.

This role focuses on building robust, production-ready AI infrastructure while enabling intuitive workflows for researchers, epidemiologists, and healthcare leaders. The work is deeply mission-driven—shaping how complex studies are conducted, how outcomes are measured, and ultimately how personalized care is delivered.

Responsibilities

• Design and implement RAG-based, agentic workflows tailored to life science research needs—including complex cohort definitions and real-time result exploration.
• Build and maintain scalable, production-grade systems for asynchronous query execution and real-time reporting, leveraging Snowflake, OpenSearch, and Amazon Neptune or other similar technologies.
• Own the full lifecycle of AI-powered features—from prototype to deployment, with a strong focus on performance, observability, and real-world impact.
• Contribute as part of a multidisciplinary product team, working alongside designers, PMs, QA, fullstack engineers, and DevOps to deliver cohesive, user-centered solutions.
• Drive innovation by experimenting with LLM-powered agents, enhancing user interaction, streamlining workflows, and generating actionable insights.
• Mentor team members, contribute to technical strategy, and help define best practices in clean, modular, and testable backend system design.
• Continuously evaluate performance, instrument observability, and iterate on production features to improve research outcomes and usability.

Qualifications

• Bachelor’s or higher degree in Computer Science, Machine Learning, or a related field.
• 5+ years of experience in software engineering, with recent work in LLM or generative AI use cases.
• Proven experience building and deploying agent-based AI systems (e.g., task orchestration, autonomous workflows).
• Strong expertise in Python, FastAPI, and backend architecture patterns
• Experience with AI orchestration frameworks such as LlamaIndex Workflows, LangChain, OpenAI, and Hugging Face.
• Familiarity with vector databases and retrieval-augmented generation (RAG) patterns using tools like OpenSearch or Pinecone.
• Hands-on experience with observability and evaluation tooling for AI workflows (e.g., LangFuse, LangSmith, custom telemetry).
• Experience working with complex or sensitive datasets, particularly in healthcare (e.g., EHR, OMOP).
• Solid grasp of software engineering best practices, including modular code design, testing, and performance profiling.
• Experience deploying services on cloud infrastructure (AWS preferred), including Lambda, Kubernetes, or equivalent.

Desired Attributes

• Familiarity with regulated or scientific domains where traceability, reproducibility, and auditability are critical.
• Experience with cohort builder or clinical research platforms, or similar tooling used for data exploration or study design.
• Understanding of event-driven systems, websocket communication, and frontend-backend integration in data-rich environments.
• Comfort collaborating across the stack—from backend services to frontend presentation and infrastructure deployment.

Our Tech Stack

• Backend: Python, FastAPI, Snowflake, DynamoDB
• AI & Orchestration: LlamaIndex, OpenAI, Anthropic, Hugging Face, OpenSearch, Amazon Neptune
• Frontend: React, TypeScript, Redux toolkit
• Infrastructure & Deployment: AWS Lambda, Kubernetes, Docker, GitHub Actions
• Architecture: Guided by