Senior AI Engineer

This is a fully remote position, open to applicants in Pennsylvania, +1 more state.

📋 Description

• Design, develop, and enhance production-level agentic AI systems aimed at addressing intricate real-world challenges.

• Create agent architectures focused on reasoning, planning, tool usage, context management, memory, and executing multi-step tasks.

• Develop secure tools and functionalities for agents to engage with data, APIs, code, and external systems.

• Establish model and inference infrastructure for both commercial and open-weight language models.

• Assess models, inference methodologies, and emerging AI capabilities for production deployment.

• Construct automated evaluation frameworks, datasets, benchmarks, and methodologies for agentic workflows.

• Enhance agent performance through prompt and context engineering, model selection, tool design, inference strategies, and system architecture.

• Create scalable APIs, services, and infrastructure to support agent execution and AI-driven product experiences.

• Design asynchronous and long-duration agent workflow systems.

• Develop secure execution frameworks for code generated by agents and computational workloads.

• Enhance observability through logging, metrics, distributed tracing, dashboards, and alert systems.

• Investigate failures across models, agents, application code, and distributed infrastructure.

• Optimize systems for latency, throughput, reliability, and infrastructure cost-efficiency.

• Translate AI research and innovative techniques into practical production enhancements.

• Collaborate with product, platform, security, and domain teams to transition AI capabilities from experimental phases to production readiness.

⛳️ Requirements

• U.S. Citizenship is mandatory.

• A minimum of 5 years of experience in building production software, AI/ML systems, distributed systems, or comparable technical systems.

• Extensive experience in designing, constructing, and operating production-grade AI agents or agent platforms.

• Proficiency in developing core agent infrastructure, including agent runtimes, tool execution, context management, memory, orchestration, or related platform functionalities.

• In-depth understanding of cutting-edge agent architectures and engineering trade-offs for reliable, production-ready agentic systems.

• Experience in designing agents that utilize tools, reason through multi-step tasks, interact with external systems, and function over prolonged or intricate workflows.

• Proven experience in building agent evaluation systems, encompassing task-level assessments, behavioral evaluations, regression testing, and production quality metrics.

• Strong knowledge of modern LLM systems, including model inference, context engineering, structured outputs, tool invocation, retrieval, model selection, and agent performance techniques.

• Capability to assess emerging models, research, and agent methodologies and adapt them into production systems.

• Strong proficiency in Python programming and production-grade software development.

• Experience in designing scalable APIs, services, asynchronous systems, and event-driven architectures.

• Familiarity with operating production services using Kubernetes and cloud platforms such as AWS, GCP, or Azure.

• Solid understanding of distributed systems, containers, service orchestration, networking, storage, and scalable architectures.

• Ability to troubleshoot complex issues across model behavior, agent execution, application code, and production infrastructure.

• Proficient in transitioning between research and engineering, prototyping ideas, rigorously evaluating them, and implementing successful strategies into production.

• Comfortable navigating a rapidly evolving field.

• Preferred: current U.S. security clearance or eligibility to obtain one with sponsorship.

• Preferred: experience in a startup or entrepreneurial environment.

• Preferred: familiarity with secure code execution environments or AI-agent sandboxes.

• Preferred: experience with multi-agent architectures, agent-to-agent communication, or distributed agent execution.

• Preferred: experience with fine-tuning, post-training, reinforcement learning, or synthetic data generation.

• Preferred: knowledge of AI observability, tracing, and debugging infrastructure.

• Preferred: experience in optimizing inference latency, throughput, GPU utilization, or model-serving costs.

• Preferred: expertise in AI security, adversarial testing, or securing agentic systems.

• Preferred: experience in government, defense, or mission-critical environments.

🏝️ Benefits

• Equal Opportunity Employer.

• Security clearance sponsorship is available for qualified candidates who can obtain one.