高级代理AI软件工程师

Location: United States – Remote
Clearance: Ability to obtain and maintain a Public Trust
LTS is seeking a Senior Agentic AI Software Engineer to build the intelligence behind the platform—the autonomous agents, orchestration layers, retrieval pipelines, reasoning workflows, and backend services that transform complex legacy software into actionable engineering knowledge.
The Agentic AI platform is designed to help engineers understand, analyze, and modernize one of the most consequential legacy software systems still operating today.
Our platform enables engineers to ask questions in plain English and receive explainable, verifiable answers traced directly back to decades of production source code. Rather than replacing engineers, we're building AI that accelerates engineering through transparency, traceability, and intelligent reasoning.
We're building an AI-native engineering platform supporting the modernization of mission-critical healthcare systems serving millions of Veterans nationwide. Every response generated by the platform must be explainable, grounded in evidence, and trusted by engineers responsible for maintaining software that millions of people quietly depend on every day.
The platform is designed for deployment across federal enterprise environments and is being engineered to align with FedRAMP security controls, Zero Trust principles, and federal compliance requirements.
The product has executive sponsorship, committed users, and a customer investing in long-term modernization. Our engineering team is intentionally small. Every engineer has meaningful ownership, significant technical influence, and the opportunity to help define how AI transforms software engineering.
We don't simply build AI-powered software—we build software with AI. This is not another chatbot.
Using LLMs, autonomous agents, AI-assisted development, parallel workflows, and model-driven engineering is simply how we work.
What You’ll Do:
Build Intelligent Agentic Systems

• Design, develop, and deploy autonomous and multi-agent AI systems capable of reasoning, planning, tool use, workflow automation, and human-in-the-loop collaboration.

• Build intelligent orchestration pipelines coordinating LLMs, specialized agents, enterprise tools, and structured reasoning workflows.

• Develop reusable agent architectures and orchestration patterns that accelerate intelligent application development across the platform.

Engineer Enterprise Retrieval & Knowledge Systems

• Design and optimize Retrieval-Augmented Generation (RAG) pipelines including document ingestion, embeddings, hybrid retrieval, reranking, semantic search, context engineering, and prompt orchestration.

• Integrate AI systems with source code repositories, enterprise documentation, APIs, structured data, and knowledge repositories.

• Ensure every AI-generated response is explainable, evidence-based, and traceable to authoritative sources.

Build Production Software

• Design and implement scalable backend services, APIs, and cloud-native applications supporting enterprise AI workloads.

• Develop distributed systems capable of serving low-latency AI experiences while maintaining security, reliability, and observability.

• Optimize performance, latency, throughput, model quality, and infrastructure cost across production AI systems.

Deliver Reliable AI

• Implement testing, evaluation, monitoring, observability, guardrails, and LLMOps practices to ensure AI systems remain trustworthy and production-ready.

• Continuously evaluate emerging models, frameworks, and engineering practices to improve platform capabilities.

• Build AI systems that behave predictably in highly regulated enterprise environments.

Collaborate Across the Product Team

• Partner closely with AI architects, platform engineers, front-end engineers, designers, and product leaders to deliver cohesive AI-powered experiences.

• Mentor engineers through technical leadership, architecture discussions, design reviews, and collaborative problem solving.

• Help establish engineering standards, reusable frameworks, and best practices across the AI engineering organization.

What We’re Looking For:

• Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Engineering, or a related technical discipline (or equivalent professional experience).

• 7+ years of professional software engineering experience designing and building distributed production systems.

• At least 3 years designing, developing, and deploying production AI applications beyond proof-of-concept environments.

• Strong proficiency in Python and modern backend software engineering.

• 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 using frameworks such as LangGraph, LangChain, LlamaIndex, Semantic Kernel, AutoGen, CrewAI, or comparable technologies.

• Strong experience designing Retrieval-Augmented Generation (RAG) architectures including embeddings, vector search, hybrid retrieval, reranking, context engineering, and grounding techniques.

• 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 with the ability to explain complex technical concepts to both engineering and business stakeholders.

• Ability to solve difficult engineering problems from first principles.

• Ability to think deeply about system architecture, reliability, and scalability.

• Passionate about explainability as model performance.

• Ability to move comfortably between distributed systems, AI frameworks, and product engineering.

• Willingness to take ownership of ambiguous, high-impact technical challenges.

• Background with using AI coding assistants, autonomous agents, and model-driven engineering workflows.

• A technically skilled engineer with a preference for building products that create lasting impact over incremental feature development.

Nice to Have:

• Experience developing multi-agent AI systems and collaborative agent workflows.

• Experience with OpenAI, Azure OpenAI, Anthropic Claude, Google Vertex AI, AWS Bedrock, or open-source LLMs.

• Experience with vector databases such as Pinecone, Weaviate, Qdrant, Milvus, or Azure AI Search.

• Experience implementing LLMOps or MLOps practices.

• Familiarity with graph databases, knowledge graphs, or dependency analysis.

• Experience working with software engineering tools, code intelligence platforms, or developer productivity products.

• Experience building AI systems in healthcare, Federal Government, or other highly regulated environments.

• Familiarity with Responsible AI, AI governance, privacy, security, and compliance best practices.

• Experience using AI coding assistants and autonomous agents as part of daily software development.

What’s In It for You?

• The Opportunity to support high-visibility federal missions

• A culture that values innovation, growth, and collaboration

• Access to cutting-edge tools and technologies

• Comprehensive benefits for you and your family

• A career path that rewards ambition and performance

If you’re ready to push boundaries, sharpen your skills, and join a team that is passionate about building what’s next, we’d love to meet you. Apply today and let’s build a future together!

LTS shares salary ranges to promote transparency. Compensation ranges are provided for informational purposes, and final compensation may vary based on experience, skills, location, and role requirements.

LTS is committed to offering eligible employees comprehensive benefits that will provide them with options intended to meet their needs and the needs of their family.

Originally posted on Himalayas