Lead AI Software Engineer - HYBRID

Lead AI Software Engineer (3 DAYS ON SITE, MUST BE A CITIZEN OR GC HOLDER) We’re hiring a senior, hands‑on engineer to build and operate production‑grade AI systems that power real business outcomes. In this role, you’ll design, ship, and run large language model (LLM) applications, intelligent agents, and automation services used across the enterprise. You’ll own the full lifecycle — from prototype to hardened production deployment — ensuring systems are reliable, observable, cost‑efficient, and safe by design. If you enjoy turning cutting‑edge AI capabilities into scalable, dependable systems that deliver measurable impact, this role is for you. What You’ll Do Build and deploy LLM-powered applications Deliver internal copilots, workflow automations, and intelligent agents. Move solutions from proof‑of‑concept to stable, SLA‑backed production services. Design for observability, rollback, and resilience from day one. Own retrieval‑augmented (RAG) systems Architect ingestion, chunking, embedding, indexing, and hybrid retrieval pipelines. Implement reranking and retrieval evaluation strategies. Continuously measure and improve retrieval quality using structured offline and online metrics. Design scalable AI infrastructure Build secure, scalable AI architectures in AWS. Implement identity controls, secrets management, and usage governance. Automate infrastructure provisioning and establish reusable patterns for AI workloads. Establish observability and reliability for AI systems Implement tracing, logging, and prompt/agent version tracking. Create evaluation dashboards, regression alerts, and canary testing strategies. Develop testing frameworks suited for non‑deterministic AI behavior. Implement guardrails and governance controls Enforce PII protections, access controls, audit logging, and review workflows. Build safeguards to manage hallucination risk, unsafe outputs, and policy violations. Drive cost and performance optimization Improve latency and throughput through batching, caching, routing, and scaling strategies. Establish clear unit economics and continuously reduce run‑rate model costs. Enable other engineers Create reusable templates, SDKs, and abstractions to accelerate safe AI development. Raise the bar on AI engineering standards and best practices across teams. Operate what you build Participate in on‑call rotations. Author runbooks and eliminate single points of failure. Treat AI systems with the same operational rigor as modern production services. What You Bring 5–10 years of professional software engineering experience. 2+ years building and deploying AI/LLM applications in production environments. Strong Python expertise and backend engineering fundamentals. Experience designing and tuning RAG systems (embeddings, hybrid search, reranking, vector databases). Familiarity with commercial and/or open‑source model providers and multi‑step orchestration. Experience with CI/CD, containers, cloud infrastructure (AWS preferred), and production operations. Hands‑on experience with observability, tracing, and monitoring tools. Strong focus on cost efficiency, quality, and risk management in AI systems. Ability to collaborate cross‑functionally and mentor other engineers. Nice to Have Experience fine‑tuning or distilling models. Familiarity with orchestration platforms for ML/data workflows. Exposure to container orchestration or high‑performance API frameworks. Experience integrating structured and warehouse‑based data sources into retrieval systems. #J-18808-Ljbffr