AI Engineer

🔥 12 hours ago

🇺🇸 United States – Remote

⏰ Full Time

🟡 Mid-level

🟠 Senior

🤖 AI Engineer

👻 Ghost score 10%

What it means: how likely this posting is sitting open without active hiring.How to read it: 60% or higher means we think this is a ghost. Lower scores are less of a worry.How we score it: age, reposts, open roles vs team size, how fast jobs close, and whether pay is listed.Fine print: an estimate from public data, not a judgment of the company. Real jobs can score high, so treat it as a hint, not a fact.

Apply Now

Find Similar Remote Jobs

Set Up Email Alert For New Jobs

📊 Check your resume score for this job

Improve your chances of getting an interview by checking your resume score before you apply.

Upload Resume

Nava Benefits

WebsiteLinkedInAll Job Openings

51 - 200 employees

Founded 2019

🏥 Healthcare

💼 Consulting

📦 Logistics

🔥 Funding within the last year

💰 $30M Series C - Nava on 2025-10

Healthcare • Consulting • Logistics

Nava Benefits is a modern employee benefits broker that pairs elite benefits advisors with an AI-powered SaaS platform (HQ) to simplify benefits administration, streamline renewals, and provide 24/7 support to employees and their families. The company helps HR teams save time, lower healthcare costs, centralize benefits documents, run audits and benchmarking, and offer AI-driven, self-serve member support and plan decision tools. Nava emphasizes alternative health plan strategies (self-funding, PBMs, captives) and positions itself as a tech-enabled extension of HR.

📋 Description

• Build and harden the platform underneath Nava’s LLM-based products • Make context management, agent state, sandboxed execution, and model routing reusable across AI use cases • Design state management and deployment patterns that allow long-running agent tasks to survive deploys, restarts, and retries • Enable agent tasks to be resumed, inspected, and replayed • Package context into zero-trust execution environments across platforms • Eject and retrieve new context as agents work • Route models to appropriate jobs and orchestrate subagents • Measure and optimize token usage and reduce cost per task as volume grows • Reduce unplanned platform work interrupting AI product teams • Document, test, trace, and evaluate shared platform patterns • Enable new engineers to adopt shared patterns quickly and catch regressions before users notice

🎯 Requirements

• Hands-on ownership of infrastructure under an LLM-based product that other engineers or users depended on • Experience with agent runtime, context or state management, orchestration, or evaluation and tracing • Experience shipping LLM features to production and managing model behavior, latency, cost, and tradeoffs • Modern full-stack development in TypeScript and/or Python • Experience integrating foundation-model APIs, tool calling, and human review into an application • Practical evaluation and tracing habits • Ability to explain decisions to product, design, and domain experts • Ability to turn product and domain problems into reusable capabilities • Experience with React, Node, TypeScript, Python, Postgres, and AWS as relevant to the stack • Experience with multiple foundation-model providers • Experience with sandboxed execution environments for agents • Langfuse for tracing and evaluation is used in the stack • No specific framework, model provider, or minimum audience size is required • Coding agents are encouraged but not required in the interview

🏖️ Benefits

• Protected space to build the AI platform • Remote-first work environment • Autonomy to thrive • Cutting-edge technology and tooling • Collaborative team • Direct line to leaders making product and platform decisions • Preparation notes ahead of each interview step