Senior / Principal AI Engineer (Generative AI, Multi-Agent Systems)Location: New York City (Hybrid - 3 days onsite)
Compensation: $200,000 - $300,000 + equity
Contact / Apply: About Our ClientOur client is building AI systems that support real clinical workflows at scale-delivering high-quality medical reasoning, documentation, and triage while meeting the reliability bar required in regulated healthcare environments. This is a high-impact role for engineers who want to ship production AI that directly affects patient care.
The RoleWe're hiring a
Senior / Principal AI Engineer to build core AI systems, clinical data infrastructure, and safety layers that enable reliable, real-time medical AI. You'll work on multi-agent reasoning, RAG pipelines over large clinical knowledge bases, model optimization, and high-throughput inference-alongside infrastructure for EHR integrations and human-in-the-loop escalation.
This is a high-ownership role suited for engineers who can move from research production and design systems that are measurable, debuggable, and safe.
What You'll BuildCore AI Systems
- Multi-agent consensus architectures where specialized models debate cases before conclusions
- RAG pipelines processing thousands of clinical guidelines structured for LLM consumption
- Fine-tuning and model distillation to improve performance and efficiency
- Real-time inference systems supporting millions of medical consultations monthly
- Custom workflows for domain-specific medical reasoning
Clinical Data Infrastructure
- HIPAA-compliant NLP pipelines extracting structured data from patient conversations
- QHIN integrations for automated EHR data retrieval and reconciliation
- Intelligent triage systems routing between AI and human providers
- Documentation generation aligned to provider-specific protocols
Safety & Scale
- Emergency detection with sub-second escalation to human oversight
- Validation layers targeting 99%+ treatment plan accuracy
- Distributed systems handling rapid growth and peak loads
- Fail-safe mechanisms for critical path decisions in regulated environments
You may also work on voice/video AI interfaces, multilingual medical NLP, predictive health modeling, and infrastructure designed for the next billion patient interactions.
Responsibilities- Design and ship production-grade LLM systems with strong evaluation, observability, and reliability guarantees
- Build multi-agent orchestration patterns (routing, tool-use, consensus, and failure handling)
- Develop retrieval + grounding layers (knowledge ingestion, indexing, ranking, citation/traceability)
- Improve model performance through fine-tuning, distillation, optimization, and latency/cost tradeoffs
- Implement safety systems: escalation paths, validation layers, monitoring, and guardrails
- Collaborate cross-functionally with product, clinical, and engineering partners to translate requirements into measurable systems
Required QualificationsEducation & Background
- CS degree or equivalent demonstrated expertise
- Hard science degrees (Physics/Math/Engineering) welcome with strong technical foundation
- Preference for graduates from top programs (where demonstrated rigor is clear)
- Preference for founders / founding engineers / substantial startup experience
- Independent problem solver who collaborates well cross-functionally
Technical Expertise
- 7+ years engineering experience with deep LLM / generative AI expertise
- Strong knowledge of foundation models (OpenAI, Anthropic, LLaMA-class models)
- Experience shipping production AI systems with real-time inference constraints
- Strong Python; experience with PyTorch and/or TensorFlow and modern AI frameworks
- Experience with prompt engineering, fine-tuning, and model optimization for specialized domains
Preferred Qualifications- AI systems for healthcare, medical, or life sciences applications
- Familiarity with medical terminology, clinical workflows, and standards (HL7, FHIR)
- Experience with medical AI safety, bias detection, and fairness in healthcare
- Domain-specific NLP experience (classification, extraction, summarization)
- Worked directly with medical professionals or in regulated healthcare environments
- Published AI/ML research (especially healthcare or safety-critical)
- Seed/Series A experience in AI or healthcare
Why This Role- Build systems that operate at the intersection of AI + safety + real clinical scale
- High ownership over architecture and reliability-shipping production AI, not demos
- Work on multi-agent reasoning, RAG, real-time inference, and healthcare integrations in one role
- Mission-driven impact: improving workflows and outcomes for patients and clinicians
Never miss an opportunity! Create an alert based on the job you applied for.
