Mid level Agentic AI Engineer

Trillion Technology Solutions•Reston, VA

About The Position

Design, build, and operate production-grade multi-agent systems for commercial and federal customers. The work covers the LangChain ecosystem, reliable agent loops, advanced retrieval architectures, ontologies that ground agent reasoning, and connecting agents to enterprise tools and to one another through MCP and A2A. The role is suited to an engineer who thinks about how agents reason, retrieve, act, recover from failure, and are evaluated and observed in production. Build single- and multi-agent applications using LangChain and LangGraph, including stateful graphs, supervisor/worker and hierarchical patterns, and human-in-the-loop checkpoints. Engineer reliable agentic loops with clear termination conditions, retry and self-correction logic, guardrails, and cost and latency budgets. Use LangSmith for tracing, debugging, prompt and dataset management, and automated evaluation, and maintain regression suites for agent behavior. Build and optimize Agentic RAG, Adaptive RAG, Corrective and Self-RAG, GraphRAG, and Cache-Augmented Generation with semantic caching. Design chunking, embedding, hybrid search, re-ranking, and query-rewriting strategies, and measure retrieval quality using faithfulness, context precision and recall, and answer relevance. Develop domain ontologies and knowledge graphs to ground agent reasoning and power GraphRAG; engineer how instructions, memory, retrieved knowledge, and tool results are assembled in the context window. Build reusable agent skills and tool libraries with clear interfaces, documentation, and versioning. Build and integrate MCP servers and clients that securely expose enterprise data, APIs, and tools to agents. Implement A2A patterns for agent discovery, capability negotiation, task delegation, and cross-vendor communication. Write production-quality Python, with tests, CI/CD, and secure coding practices. Take agents from prototype to production with product, data, and platform teams, and contribute to architecture decisions, code reviews, and internal standards for agentic systems.

Requirements

Bachelor's degree in Computer Science, Engineering, or a related field, or equivalent experience.
10 years of software engineering experience, with at least 4 years building LLM-powered applications.
Hands-on production experience with LangChain, LangGraph, and LangSmith.
Demonstrated experience designing agentic loops, tool calling, memory, and multi-agent orchestration.
Practical experience implementing several RAG variants, including Agentic, Adaptive, GraphRAG, and Cache RAG/CAG, and evaluating their quality.
Experience designing ontologies or knowledge graphs and applying them to retrieval or reasoning.
Strong context engineering and prompt design for complex agent workflows.
Experience building or integrating MCP servers and clients, and working knowledge of the A2A protocol.
Proficiency in Python, REST/gRPC APIs, and asynchronous programming.
Solid grasp of LLM failure modes, including hallucination, prompt injection, and context limits, and their mitigations.

Responsibilities

Build single- and multi-agent applications with LangChain and LangGraph, including stateful graphs, supervisor/worker and hierarchical patterns, and human-in-the-loop checkpoints.
Engineer reliable agentic loops with clear termination conditions, retry and self-correction logic, guardrails, and cost and latency budgets.
Tune iteration depth, tool-call strategy, memory handling, and state persistence so agents behave predictably.
Use LangSmith for tracing, debugging, prompt and dataset management, and automated evaluation; maintain regression suites for agent behavior.
Build and optimize Agentic RAG, Adaptive RAG, Corrective and Self-RAG, GraphRAG, and Cache-Augmented Generation with semantic caching.
Design chunking, embedding, hybrid search, re-ranking, and query-rewriting strategies; measure retrieval quality with faithfulness, context precision and recall, and answer relevance.
Develop domain ontologies and knowledge graphs that ground agent reasoning and power GraphRAG.
Engineer how instructions, memory, retrieved knowledge, and tool results are assembled in the context window.
Build reusable agent skills and tool libraries with clear interfaces, documentation, and versioning.
Build and integrate MCP servers and clients that securely expose enterprise data, APIs, and tools to agents.
Implement A2A patterns for agent discovery, capability negotiation, task delegation, and cross-vendor communication.
Write production-quality Python with tests, CI/CD, and secure coding practices.
Take agents from prototype to production with product, data, and platform teams.
Contribute to architecture decisions, code reviews, and internal standards for agentic systems.