Third Way Health is seeking a Senior AI / ML Engineer to build next-generation AI systems that help millions of patients access care faster. You will architect and operate production ML infrastructure handling thousands of hours of service interactions daily in a highly regulated healthcare environment. This is a high-impact individual contributor role.
What You'll Do
- Architect and build large-scale AI systems that integrate high-volume voice, text, and contextual event streams with extensive knowledge bases to deliver real-time recommendations, automations, and decision support.
- Design and operate workflow-oriented AI systems, including DAG-based execution graphs, stateful pipelines, and agent-driven workflows with clear observability, reproducibility, and fault tolerance.
- Build agent architectures spanning agent-to-agent coordination, feedback loops, tool-calling systems, and long-running autonomous workflows, balancing control, safety, and adaptability.
- Design and implement data models, feature pipelines, and APIs to support model training, low-latency inference, and continuous learning.
- Develop predictive, real-time analytics systems that combine streaming data, ML inference, and event-driven triggers to surface insights and automate actions at scale.
- Implement and maintain end-to-end ML platforms, including model training, evaluation, deployment, online inference, monitoring, and drift detection.
- Partner closely with product managers, data scientists, and QA engineers to translate experimental models into reliable, production-grade AI services.
- Identify, diagnose, and resolve performance and scaling bottlenecks across data pipelines, inference services, and orchestration layers as production workloads grow.
What We're Looking For
- 5+ years of software engineering experience, with 3+ years focused on machine learning or applied AI systems.
- Strong proficiency in Python, particularly for ML pipelines, frameworks, inference services, and APIs (e.g., scikit-learn, Sanic API, PyTorch Lightning, Pydantic AI, LangGraph, Bedrock, OpenAI / Anthropic SDKs).
- Experience designing ML-centric data architectures, including feature stores, vector databases, and time-series systems for monitoring and analytics.
- Hands-on experience with cloud-native inference: containerized model serving, autoscaling, GPU/accelerator workloads, and low-latency production deployments.
- Experience operating end-to-end MLOps platforms (e.g., MLflow, Kubeflow), including CI/CD for models, experiment tracking, and rollout strategies.
- Solid understanding of workflow orchestration (graph-based execution, retries, state management) in ML and agent-based systems.
- Excellent communication skills, with the ability to collaborate effectively across engineering, product, and non-technical stakeholders.
- Strong interest in healthcare innovation and building AI systems that meaningfully improve health outcomes.
- Working knowledge of AI safety, bias detection, and responsible AI practices.
Nice to Have
- Experience building AI systems in healthcare or regulated environments, with familiarity with standards such as HIPAA, GDPR, or FDA guidance.
- Proven experience leading complex technical initiatives and mentoring junior engineers.
- Strong applied knowledge of event-driven architectures and streaming systems (Kafka, Pub/Sub, Kinesis, RabbitMQ).
- Hands-on experience designing and operating vector search, RAG pipelines, and hybrid retrieval systems.
- Experience with agent frameworks, multi-agent coordination patterns, and long-running agent loops in production environments.
- Familiarity with real-time analytics stacks combining streaming data, ML inference, and operational dashboards.
Technical Stack
- Python, scikit-learn, Sanic API, PyTorch Lightning, Pydantic AI, LangGraph, Bedrock, OpenAI SDK, Anthropic SDK
- MLflow, Kubeflow
- Kafka, Pub/Sub, Kinesis, RabbitMQ
Third Way Health is an equal opportunity employer.





