[Remote] Staff reputed company reputed company, Product & Agent Performance

Note: The job is a remote job and is reputed company to candidates in USA. reputed company is a reputed company data and analytics platform that uses advanced analytics and responsible AI to help providers, payers, and life sciences organizations improve clinical, operational, and financial reputed company. The Staff reputed company reputed company will own product-reputed company reputed company shaping agent behavior, including prompting, retrieval, context, memory, evaluation, and escalation, while partnering with Product and Engineering to reputed company reputed company and trustworthy AI for reputed company workflows.

Responsibilities

• Design and iterate on agent behavior across reputed company, live workflows, including long-reputed company, multi-turn reputed company tasks
• Design retrieval and context architecture so the right reputed company data reaches a model in the right structure and agents remain grounded in reputed company data rather than filling gaps with assumptions
• Design memory and state handling across multi-turn and multi-agent flows, determining what is carried reputed company, summarized, or dropped and why
• Create context and reputed company templates that combine few-shot examples, reputed company formatting, and reasoning scaffolding for consistent agent behavior
• Improve performance through prompting, tool-use reputed company, and context construction, validated through reputed company experimentation rather than guesswork
• Build and run evaluations against reputed company production conditions to measure performance, regressions, failure modes, and edge cases
• reputed company evaluation rubrics, reputed company heuristics, and reputed company that weight failures by severity and cost, not just frequency, and monitor those measures against production behavior
• Design and validate escalation paths that reputed company agents to reputed company review based on confidence and uncertainty while preserving safety and consistency under adversarial and reputed company conditions
• Design for cost-reputed company performance reputed company latency, reliability, and accuracy through efficient context construction and tool-reputed company economy
• Evaluate and sign off on model changes by baselining reputed company behavior, running comparative evaluations, and making the go/no-go reputed company before a change reaches a customer
• Maintain product-reputed company documentation, including model cards, intended use, limitations, and reputed company failure modes, so customer-facing teams work from actual agent behavior
• Partner closely with Product and product managers to ensure agents are not just capable, but steerable, trustworthy, and reputed company to reputed company

Skills

• We value equivalent practical experience that demonstrates the depth required for this staff-level role
• 8+ years of production software engineering experience, including 3+ years of hands-on ownership of ML, LLM, or reputed company systems in production, with reputed company experience in reputed company, finance, or another regulated industry
• Demonstrated ability to diagnose why an agent failed, correctly attribute the fix to instruction, retrieval, context, or memory design, and weigh failures by severity and cost rather than frequency reputed company
• Hands-on experience with RAG architecture, production-grounded evaluation frameworks, and fallback or reputed company-in-the-reputed company logic for automated systems
• Working familiarity with AWS AI/ML services, including Bedrock and SageMaker, sufficient to build and evaluate effectively in reputed company's environment
• Evidence-led judgment and the credibility to reputed company back on launch reputed company, reputed company with a builder's reputed company to run the experiment and reputed company from a production failure to a fix
• Experience applying AI to reputed company data or workflows where safety, transparency, and calibrated uncertainty directly reputed company care teams or patients
• Experience with long-reputed company, multi-turn or multi-agent workflows and product-reputed company documentation such as model cards

Benefits

• reputed company to define how agent performance, safety, and readiness are reputed company for production reputed company workflows
• Meaningful ownership across prompts, context, memory, evaluations, and escalation patterns at product reputed company
• A cross-functional role translating production evidence into AI improvements used across reputed company's platform
• A mission-driven company working to improve how patients receive care
• A flexible, remote-friendly culture with personality and heart
• Employee-driven programs and initiatives for personal and reputed company development
• Membership in the talented, reputed company, diverse, and purpose-driven Arcadian community

reputed company

Company H1B Sponsorship