Senior Agentic AI Software Engineer

Salary: $146,300 - 178,100 per year

Requirements:

• Bachelors degree in Computer Science, Software Engineering, Artificial Intelligence, Engineering, or a related technical field, or equivalent professional experience; a bachelors degree is preferred.
• At least 7 years of experience designing and building distributed production systems.
• At least 3 years of experience designing, developing, and deploying production AI applications.
• Strong TypeScript proficiency, working competency in Python and other languages, and substantial modern backend engineering experience.
• Experience building enterprise APIs, microservices, and cloud-native applications.
• Hands-on experience developing applications powered by large language models (LLMs) and generative AI.
• Experience building agentic AI solutions with frameworks such as LangGraph, LangChain, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or comparable technologies.
• Strong experience designing RAG architectures, including embeddings, vector search, hybrid retrieval, reranking, context engineering, and grounding.
• Experience integrating AI systems with enterprise APIs, databases, cloud platforms, and business applications.
• Experience with Docker, Kubernetes, Git, CI/CD pipelines, and modern DevOps practices.
• Strong understanding of software architecture, testing, observability, debugging, and production operations.
• Excellent communication skills, including the ability to explain complex technical concepts to engineering and business stakeholders.
• Ability to solve difficult engineering problems from first principles and reason deeply about architecture, reliability, and scalability.
• Passion for explainability and the ability to work across distributed systems, AI frameworks, and product engineering.
• Willingness to own ambiguous, high-impact technical challenges; experience with AI coding assistants, autonomous agents, and model-driven engineering workflows is also sought.
• Ability to obtain and maintain a Public Trust clearance.
• U.S. citizenship or lawful permanent resident status is required for project eligibility.
• Nice to have: experience with multi-agent systems, commercial or open-source LLM platforms, vector databases, LLMOps or MLOps, graph databases or knowledge graphs, code intelligence or developer productivity products, regulated environments, and Responsible AI, governance, privacy, security, or compliance practices.

Responsibilities:

• Design, develop, and deploy autonomous and multi-agent AI systems for reasoning, planning, tool use, workflow automation, and human collaboration.
• Build orchestration pipelines that coordinate LLMs, specialized agents, enterprise tools, and structured reasoning workflows.
• Create reusable agent architectures and orchestration patterns for intelligent applications across our platform.
• Design and optimize RAG pipelines, covering ingestion, embeddings, hybrid retrieval, reranking, semantic search, context engineering, and prompt orchestration.
• Connect AI systems to source-code repositories, enterprise documentation, APIs, structured data, and knowledge repositories.
• Ensure AI-generated responses are explainable, evidence-based, and traceable to authoritative sources.
• Build scalable backend services, APIs, and cloud-native applications for enterprise AI workloads.
• Develop distributed systems that deliver low-latency AI experiences with security, reliability, and observability.
• Optimize production AI systems for performance, latency, throughput, model quality, and infrastructure cost.
• Implement testing, evaluation, monitoring, observability, guardrails, and LLMOps practices to keep AI systems reliable and production-ready.
• Assess emerging models, frameworks, and engineering practices to improve platform capabilities, and build predictable AI systems for regulated enterprise settings.
• Collaborate with AI architects, platform and front-end engineers, designers, and product leaders to deliver cohesive experiences.
• Mentor engineers through technical leadership, architecture discussions, design reviews, and collaborative problem solving.
• Establish engineering standards, reusable frameworks, and best practices across our AI engineering organization.

Technologies:

• Agentic AI
• AI
• Backend
• CI/CD
• Cloud
• DevOps
• Docker
• Git
• Support
• Kubernetes
• LLM
• MLOps
• Python
• RAG
• Security
• TypeScript
• microservices
• AWS
• Azure

More:

We are hiring a Senior Agentic AI Software Engineer for a remote role in the United States. At LTS, we are developing an AI-native engineering platform to help teams understand and modernize a major legacy software system supporting mission-critical healthcare services for millions of Veterans. Our platform provides explainable answers grounded in production source code; it is designed to support engineers, not replace them. The product has executive sponsorship, committed users, and a customer investing in long-term modernization. Our intentionally small team offers meaningful ownership and technical influence. We build software with AI, using LLMs, autonomous agents, AI-assisted development, parallel workflows, and model-driven engineering. The platform is intended for federal enterprise deployment and is being engineered to align with FedRAMP controls, Zero Trust principles, and federal compliance requirements. Compensation is $146,300–$178,100 per year. We offer comprehensive benefits for employees and families, including 401(k) matching, dental, health, life, and vision insurance, a health savings account, paid time off, employee discounts, and a referral program. We also offer opportunities to support high-visibility federal missions, work with advanced tools, and grow in a collaborative, innovative culture.

last updated 45 week of 2026