AI Orchestration Engineer

Title: AI Orchestration Engineer

Location: Hybrid, Palo Alto, CA — Tuesday through Thursday

About Us

Sage Care is a fast-growing Series A healthcare technology startup founded by leaders from Apple, Uber, and Carbon Health. We recently emerged from stealth with $20 million in funding led by Yosemite, and investors including General Catalyst, Metrodora Ventures (co-founded by Chelsea Clinton), OVTR.VC, SV Angel, Liquid 2 Ventures, Seven Stars, Refract Ventures, AME Cloud Ventures, and Apolo Ohno.

Our founding story and vision were recently profiled in Forbes, highlighting Sage Care’s mission to build an “air-traffic-control system for healthcare.”

With a strong customer pipeline, Sage Care is transforming healthcare by simplifying care navigation. Our platform makes it easier for patients to find the right doctor, helps providers focus on those who need them most, and ensures faster access to care. By harnessing clinically grounded AI and real-time optimization, we improve operational efficiency, increase system capacity, and deliver better patient outcomes at scale.

Job Overview

An AI Orchestration Engineer focuses on designing, implementing, and maintaining the “glue” that coordinates multiple AI models, agents, and workflows into a cohesive system. Rather than just building models, this role ensures they interact effectively, scale properly, and integrate seamlessly into real-world applications.

What You’ll Do:

• Workflow & Pipeline Orchestration

  • Build and manage directed workflows (DAGs, state machines, LangGraph flows)

  • Define how data and context move between AI models, APIs, and humans in the loop

• Multi-Agent Collaboration

  • Design coordination strategies for multiple AI agents with specialized roles

  • Implement arbitration logic to merge outputs, resolve conflicts, and dynamically route tasks

• Integration & Infrastructure

  • Connect AI systems with vector databases, APIs, cloud platforms, and external data sources

  • Handle orchestration across distributed environments (Kubernetes, serverless)

• Reliability & Error Handling

  • Implement retries, fallbacks, and guardrails to keep workflows stable

  • Ensure systems degrade gracefully when AI outputs are uncertain or incorrect

• Optimization & Evaluation

  • Tune orchestration for cost, latency, and accuracy

  • Build observability dashboards, logging, and metrics to measure workflow success

Example Use Cases You Might Work On:

• Routing patient triage queries across different AI agents (diagnosis, risk scoring, recommendations)

• Coordinating a retrieval-augmented generation (RAG) pipeline: retriever → ranker → LLM

• Running human-in-the-loop workflows where AI suggests and humans validate

• Ensuring continuity across multi-step processes, such as decision trees for medical protocols

What We’re Looking For:

• Programming: Proficiency in Python, TypeScript, or Go (depending on orchestration stack)

• Frameworks: Experience with LangGraph, LangChain, or Ray

• Infrastructure: Strong knowledge of Docker, Kubernetes, CI/CD pipelines, and observability tools (Prometheus, Grafana)

• AI/ML Understanding: Familiarity with LLMs, RAG systems, embeddings, and multi-agent patterns

• Data Systems: Experience with vector databases (FAISS, Pinecone, Weaviate) and caching systems (Redis, Memcache)

Nice to Have:

• Hands-on experience with healthcare workflows or regulated environments

• Exposure to human-in-the-loop AI systems

• Background in reliability engineering or distributed systems

Why You’ll Love Working Here:

• Mission-driven work at the intersection of AI and healthcare

• Collaborative team that values curiosity, creativity, and ownership

• Flexibility to experiment with the newest orchestration frameworks and AI infrastructure