Senior AI Engineer

Senior AI Engineer Symphony Platform

Reports to: Principal AI Platform Engineer
Location: United States (Remote with preference for EST or CST)

Role Overview

The Senior AI Engineer is a deep technical builder responsible for implementing and optimizing the core components of the Symphony agentic AI platform including multi-agent execution, orchestration logic, workflow services, retrieval pipelines, and interoperability connectors across healthcare data domains.

This role partners closely with the Principal AI Platform Engineer (technical owner of Symphony) and works across product, data, and integration teams to transform Symphony into a scalable, secure, cloud-native platform powering Utilization Management (UM), Care Management (CM), Disease Management (DM), and next-gen agentic AI clinical workflows.

The ideal candidate is a senior-level engineer who is comfortable designing and building LLM-powered systems, retrieval pipelines, microservices, and distributed workflows in a fast-moving environment.

Key Responsibilities

AI Agent & Workflow Development

• Design, build, and maintain Symphony s multi-agent execution framework, including orchestration, agent routing, memory, context management, and decision engines.
• Develop LLM-powered workflows (RAG pipelines, hybrid retrieval, tool-use, reasoning agents, summarization, rule-based + generative blends).
• Implement guardrails, evaluation logic, and reliability patterns (traceability, deterministic fallbacks, safety checks).

Platform Engineering

• Build platform-level services, APIs, microservices, and event-driven components that support next-gen AI workflows.
• Develop internal SDKs, utilities, and developer-facing tools to standardize how teams build on top of Symphony.
• Implement observability, logging, monitoring, vector retention policies, and agent performance instrumentation.

Interoperability & Data Engineering

• Build connectors for healthcare domains including FHIR R4, claims data, EHR data, HL7, X12, UM/CM systems, legacy sources, and cloud data platforms.
• Develop vectorization pipelines, embedding generation, and retrieval systems optimized for clinical and administrative data.

Cloud-Native Operations

• Support deployment to AWS + Kubernetes, including containerization, CI/CD pipelines, IAM, Secrets Management, and environment configuration.
• Implement highly scalable architectures that meet enterprise performance targets across UM/CM/DM workloads.

Collaboration & Technical Leadership

• Work with Product Management to translate requirements into technical execution plans.
• Participate in architecture reviews, design critiques, code reviews, and engineering standards development.
• Collaborate with AI/ML, data, and integration teams to ensure cohesive platform evolution.
• Provide mentorship to junior engineers and contribute to engineering best practices.

Required Skills & Experience

Engineering Experience

• 5 10+ years of software engineering experience building production systems.
• Strong expertise in Python or TypeScript/Node.js, with emphasis on backend engineering.
• Deep experience with LLM and agent frameworks such as:
  • LangChain, LangGraph, Haystack, Semantic Kernel, or custom agentic frameworks.

AI Systems Engineering

• Hands-on experience with vector databases (Pinecone, Weaviate, Milvus, OpenSearch, pgvector).
• Solid understanding of embeddings, similarity search, evaluation techniques, and retrieval optimization.
• Experience building RAG systems, structured prompting workflows, and model integration patterns.

Distributed Systems & Platform Architecture

• Strong understanding of microservices, event-driven architectures, and workflow/orchestration engines.
• Experience implementing scalable APIs, message queues, and asynchronous compute.

Cloud & DevOps

• Experience deploying and maintaining workloads in AWS including Gov Cloud (EKS, Lambda, EC2, S3, Step Functions, IAM, CloudWatch).
• Hands-on Kubernetes (EKS preferred), Docker, and CI/CD pipelines.

Ways of Working

• Ability to thrive in a high-velocity, iterative build environment with evolving requirements.
• Comfort working in ambiguous environments, creating structure, and delivering production-grade solutions.

Healthcare Data & Domain Experience

• Familiarity with claims systems, FHIR R4, HL7, X12 270/271/278, care management workflows, clinical terminology (LOINC, SNOMED).
• Experience building systems for UM/CM/DM or payer/provider interoperability.
• Experience building Core Administrative Processing Systems (Claims, Call Center, EDI, etc.)

AI Platform & Data Platforms

• Experience with Palantir Foundry and/or Palantir AIP, especially in ontology design, pipelines, or operational object workflows.
• Experience building shared libraries, SDKs, or internal developer platforms.

Security & Compliance

• Understanding of HIPAA, NIST 800-53, NIST CSF 2.0, Fedramp, SOC-2, HiTrust, PHI handling, access control patterns, encryption, and audit requirements.