AI Platform Engineer - LLM Agents & RAG

Careers Signant Health

1d • Remote

About The Position

The AI Engineer – Platform will build and optimize Signant Health’s AI platform and intelligent agents that automate workflows across the organization. This role sits at the intersection of production software engineering and applied generative AI—delivering agentic applications, RAG capabilities, evaluation frameworks, and guardrails that ensure safe, reliable, and compliant AI outcomes.

Requirements

• 5+ years of software engineering experience with strong proficiency in Python and production systems
• 2+ years building and deploying AI/ML or LLM-based applications in production
• Hands-on experience with prompt engineering and context management for LLM apps
• Proven experience implementing RAG systems and using vector databases/knowledge stores
• Experience building evaluation metrics/frameworks for AI quality and reliability
• Strong engineering fundamentals (APIs, distributed systems, Git, CI/CD, testing)
• Solid understanding of AI safety and security principles (guardrails, hallucination mitigation, prompt injection prevention)

Nice To Haves

• Experience with autonomous/agentic workflows (tool use, planning, state management)
• Experience optimizing model inference (performance/cost trade-offs; deployment optimization)
• Observability experience for AI systems (monitoring, logging, alerting, dashboards)
• Experience operating in regulated environments (GDPR, HIPAA, SOC2 or similar)
• Healthcare, life sciences, or clinical trial technology experience
• Experience with AI safety testing/red-teaming approaches
• Familiarity with common AI platforms/frameworks and model providers (agent frameworks and managed LLM services)
• Willingness to collaborate across teams and communicate clearly with technical and non-technical stakeholders

Responsibilities

• Build AI-powered agents that automate multi-step workflows and integrate with internal tools and data sources
• Implement Retrieval-Augmented Generation (RAG) solutions to ground responses in trusted knowledge
• Develop and maintain AI platform components and reusable services (APIs, pipelines, orchestration)
• Design evaluation frameworks to measure quality (accuracy, relevance, safety) and improve performance over time
• Monitor production AI systems; optimize latency, cost, reliability, and user outcomes
• Engineer datasets and support fine-tuning and model selection decisions (RAG vs fine-tuning vs prompting)
• Implement guardrails and security controls (prompt injection resistance, sensitive data handling, safe output behaviors)
• Partner with Security/Legal/Compliance to align AI implementations to governance and regulatory expectations
• Document designs, standards, and operational runbooks; participate in code reviews and knowledge sharing

What This Job Offers

• Job Type: Full-time
• Career Level: Mid Level
• Education Level: No Education Listed