Lead AI Software Engineer

Liberty Personnel Services, Inc. is seeking a senior, hands-on AI software engineer to design, build, and operate production-grade AI systems that drive real business outcomes. You will own the end-to-end lifecycle from prototyping LLM applications to production deployment, including intelligent agents and automation services, in a hybrid work setup based in Wilmington, Delaware.

Responsibilities

• Develop and deploy applications powered by large language models.
• Deliver internal copilots, workflow automations, and intelligent agents.
• Advance solutions from proof-of-concept to reliable, SLA-backed production services.
• Incorporate observability, rollback plans, and resilience from day one.
• Own retrieval-augmented generation (RAG) systems.
• Design ingestion, embeddings, chunking, indexing, and hybrid retrieval pipelines.
• Implement reranking and evaluation strategies for retrieval quality.
• Continuously measure and improve retrieval performance using structured offline and online metrics.
• Architect scalable AI infrastructure in AWS with security considerations.
• 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 with tracing, logging, and version tracking for prompts and agents.
• Create evaluation dashboards, regression alerts, and canary testing strategies.
• Develop testing frameworks tailored for non-deterministic AI behavior.
• Implement guardrails and governance controls to regulate AI outputs and policies.
• Enforce PII protections, access controls, audit logging, and review workflows.
• Build safeguards to mitigate hallucination risk, unsafe outputs, and policy violations.
• Drive cost and performance optimization through batching, caching, routing, and scaling strategies.
• Establish clear unit economics and continually reduce run-rate model costs.
• Provide reusable templates, SDKs, and abstractions to accelerate safe AI development for teams.
• Raise the bar on AI engineering standards and best practices across teams.
• Operate what you build by participating in on-call rotations and writing runbooks to prevent single points of failure.
• Treat AI systems with the same operational rigor as modern production services.

Requirements

• 5 to 10 years of professional software engineering experience.
• At least two years building and deploying AI/LLM applications in production environments.
• Proficiency in Python and strong backend engineering fundamentals.
• Experience designing and tuning RAG systems, including embeddings, hybrid search, reranking, and vector databases.
• Familiarity with commercial or open-source model providers and multi-step orchestration.
• Experience with CI/CD, containerization, 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.

Technologies

Python, AWS, vector databases, CI/CD, containers

Nice to have

• Experience fine-tuning or model distillation.
• Familiarity with orchestration platforms for ML and data workflows.
• Exposure to container orchestration or high-performance API frameworks.
• Experience integrating structured and warehouse-based data sources into retrieval systems.