Staff AI Engineer
About The Position
CHG Healthcare is seeking a Staff AI Engineer to join our AI Engineering team. The Engineering team designs, builds, and maintains the technology platforms and software solutions that power CHG's staffing and healthcare businesses. As a Staff AI Engineer, you will serve as a technical leader and mentor across the team, setting technical direction for AI-powered products and driving high-quality software delivery, architectural decisions, and engineering excellence in an AI-driven product development environment. The Staff AI Engineer is a force multiplier who sets technical direction for AI-powered products across multiple teams. Impact comes through architecture, shared platforms, standards, and people rather than single-team deliverables. The role designs and owns production LLM and agentic systems—built in TypeScript and Python on AWS, Amazon Bedrock, and Anthropic models, with data on Snowflake and Postgres—and is accountable to leadership for the reliability, security, cost, and quality of the organization’s biggest AI technical bets.
Requirements
- Comfortable with ambiguity, high agency, and systems thinking; strong business acumen and product judgment at the org level.
- Software Architecture for AI systems — mastery of architecture for AI-heavy systems (long-running agents, async orchestration, failure isolation); sets patterns across multiple teams.
- LLM Integration — deep command of model behavior across providers and versions (Anthropic, Amazon Bedrock); prompt/context engineering, structured outputs, and fine-tuning-vs-prompting judgment.
- Context & Retrieval at scale — RAG, embeddings and vector search, multi-source federation, and permission-aware retrieval over Snowflake and Postgres.
- Agentic Systems & Orchestration — multi-agent coordination, long-running workflows, integration standards (MCP), and constraining agents safely at scale.
- AI Quality & Operations — eval frameworks, observability and tracing, reliability, incident response, and cost/performance optimization for nondeterministic systems.
- Security & Responsible AI — securing agentic systems, red-teaming, guardrails, and privacy/compliance controls.
- Technical Proficiency — expert across TypeScript and Python; AWS, containerization, and CI/CD; data modeling on Snowflake and Postgres.
- AI-Augmented Development — designs how teams adopt AI coding agents safely (review gates, provenance, CI integration) to multiply output.
- Influence & Leadership — org-level communication and RFCs that align teams, cross-functional partnership, and mentorship that develops engineers across teams.
- M.S. / B.S. in Computer Science or related STEM discipline
- 9+ years of proven software engineering experience, including hands-on delivery of production LLM/AI systems
Nice To Haves
- Production experience with TypeScript/Node.js and Python
- Hands-on experience with Amazon Bedrock and Anthropic (Claude) models, and multi-provider LLM integration
- Experience with Snowflake and Postgres, including data modeling and permission-aware retrieval
- Experience with AWS, containerization (Docker/Kubernetes), and CI/CD pipelines (GitHub Actions/Jenkins)
- Experience building agentic systems with MCP and tool orchestration, and eval-driven development of AI features
Responsibilities
- Set architecture patterns for AI-heavy systems—state management for long-running agents, async orchestration, and failure isolation—across multiple teams, and prevent architectural drift.
- Design and own production LLM and agentic systems on Amazon Bedrock and Anthropic models: prompt and context design, structured outputs, model selection, and migration strategies for model upgrades across providers and versions.
- Architect shared platforms adopted across teams—retrieval/context (RAG, embeddings, permission-aware retrieval over Snowflake and Postgres), agent and tool-orchestration frameworks (including MCP), and evaluation harnesses.
- Establish AI quality, observability, and reliability standards: continuous evaluation and drift detection, privacy-safe tracing, graceful degradation, fallbacks, rate-limit handling, and SLOs for nondeterministic systems.
- Lead AI and application security and Responsible AI at scale—prompt-injection defense, tool-permission and sandboxing models, red-teaming, guardrails—and translate privacy and compliance obligations into technical controls.
- Own the economics of AI features—token efficiency, caching, model routing, latency, and build-vs-API analysis—and set cost and optimization standards across teams.
- Define how teams safely integrate AI agents into the TypeScript and Python SDLC, including review gates, provenance, and CI integration.
- Set technical direction through RFCs and cross-team programs, act as a trusted tiebreaker, and mentor and develop senior engineers and future tech leads across teams.
Benefits
- 401(k) retirement plan with company match
- Traditional healthcare benefits such as medical and dental coverage
- Onsite health centers
- Corporate wellness programs
- Free behavioral health appointments
- Flexible work schedules - including work-from-home options available
- Recognition programs with rewards including trips, cash, and paid time off
- Family-friendly benefits including paid parental leave, fertility coverage, adoption assistance, and marriage counseling
- Tailored training resources including free LinkedIn learning courses
- Volunteer time off and employee-driven matching grants
- Tuition reimbursement programs
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
