Applied AI/ML Principal Engineer

Applied AI/ML Principle Engineer

What You'll Do

• Agent Architecture & Design: Lead the technical design of multi-agent workflows, orchestrating LLMs, RAG pipelines, and knowledge integration to solve complex, multi-layered problems. Build robust systems that reason across structured and unstructured data.
• Production-Grade Agentic Systems: Build, prototype, and scale end-to-end AI agents that are production-ready for an enterprise platform, not proof-of-concepts. Design system architectures that prioritize reliability, usability, and auditability, with clear human-in-the-loop interfaces for domain experts.
• Reliability & Scaling: Take prototypes from isolated testing environments to scaled production systems. Design and deploy high-availability model endpoints with health checks, error handling, retries, and fallback mechanisms.
• Evaluation & Guardrails: Implement evaluation frameworks and guardrails to identify and eliminate logical errors, hallucinations, and bias before they reach production decision-making.
• Data Engineering Collaboration: Partner with data engineers to build and optimize ingestion and processing pipelines that feed agentic and ML systems with high-quality, well-governed data.
• MLOps & Observability: Deploy and monitor models and agents in production using modern MLOps tooling, tracking performance, latency, and model/behavior drift over time.
• Cross-Functional Partnership: Work closely with Product Managers, Engineers, and domain stakeholders to translate ambiguous business problems into concrete technical specifications. Act as a self-sustaining technical leader who unblocks integration hurdles in partnership with engineering teams.

What We're Looking For
Core Qualifications

• Bachelor's, Master's, or Ph.D. in Computer Science, Data Science, Engineering, or related field.
• Proven experience building, training, and deploying ML and NLP systems, particularly LLM- and transformer-based applications.
• Hands-on experience with agent frameworks (e.g., LangChain/LangGraph) for production systems and enterprise platforms including Q&A systems, autonomous agents, or complex workflow automation.
• Strong software engineering fundamentals: Python, Git/GitHub, CI/CD.
• Experience working in a regulated, audit-sensitive, or high-stakes domain where deterministic accuracy and auditability are paramount.
• Experience building agentic tools and systems that have shipped to production, not just internal demos.
• Experience with classical ML modeling (time-series forecasting, tree-based models) alongside modern LLM/GenAI tooling.
• Expertise deploying observability/monitoring tooling to track model performance, latency, and drift in live systems.
• Excellent communication and storytelling skills, with a proven ability to translate complex technical architectures and probabilistic model behavior to non-technical executive leadership.