AI Engineer

Jobtailor

Maryland

On-site

USD 180,000 - 240,000

Full time

2 days ago

Be an early applicant

Application generator

Turn this role into an interview — a resume and cover letter built around what this employer wants.

Get past ATS filters

Job summary

Jobtailor is seeking a seasoned AI/ML engineer to design and deploy multi-agent systems, leveraging LangChain, LangGraph, and AutoGen. The role focuses on production-grade ML pipelines, RAG architectures, and knowledge graphs to drive reliable, scalable AI solutions.

You will work across cloud environments (AWS/Azure), fine-tune LLMs/SLMs, and implement evaluation frameworks to ensure safety and performance in real-world deployments. A TS/SCI polygraph is required.

Qualifications

2+ years of software development experience.
2+ years as ML engineer building production-grade ML solutions.
Experience with LangChain, LangGraph, AutoGen, and related tools.
Experience with cloud environments (AWS/Azure) and designing scalable services.
Experience with MCP for tool integration and A2A for agent collaboration.
Experience with RAG and knowledge graphs (Neo4j/NebulaGraph).
Experience fine-tuning LLMs/SLMs (Hugging Face, PEFT, LoRA).
Experience evaluating LLM performance and building observation layers (Grafana, Langfuse, LangSmith, Phoenix).
Knowledge of microservice design and edge computing.
TS/SCI clearance with polygraph required.
Bachelor’s degree; Master’s preferred; Doctorate a plus.

Responsibilities

Design and implement intelligent agent architectures that can reason, plan, and take actions using LangChain, LangGraph, and AutoGen.
Develop and deploy multi-agent systems using MCP and A2A protocols for communication, tool usage, and collaborative task solving.
Build advanced RAG pipelines integrating unstructured data with Knowledge Graphs to enhance reasoning accuracy and context retention.
Fine-tune SLMs for specific domains and optimize them for edge device performance, including ONNX, GGML, or Ollama.
Develop evaluation frameworks to test agent reliability, safety, and performance, moving systems from prototype to production, including ReAct loops and human-in-the-loop.
Shift AI strategy from passive LLM chatbots to proactive, multi-agent orchestrations.

Skills

LangChain

LangGraph

AutoGen

MCP

A2A

RAG Architecture

Knowledge Graphs

Production-Grade ML Solutions

Fine-Tuning LLMs

Education

Bachelor's degree

Master's degree in CS/AI

Doctorate in CS/Statistics a plus

TS/SCI Clearance with Polygraph

Tools

Docker

Kubernetes

Grafana

Langfuse

LangSmith

Phoenix

Hugging Face

PEFT

LoRA

Neo4j

Job description

Design and implement intelligent agent architectures that can reason, plan, and take actions using LangChain, LangGraph, and AutoGen
Develop and deploy multi-agent systems using MCP and A2A protocols for communication, tool usage, and collaborative task solving
Build advanced RAG pipelines integrating unstructured data with Knowledge Graphs to enhance reasoning accuracy and context retention
Fine-tune SLMs for specific domains and optimize them for edge device performance, including ONNX, GGML, or Ollama
Develop evaluation frameworks to test agent reliability, safety, and performance, moving systems from prototype to production, including ReAct loops and human-in-the-loop
Shift AI strategy from passive LLM chatbots to proactive, multi-agent orchestrations

Requirements

2+ years of experience in software development
2+ years of experience as an ML engineer building production-grade ML solutions using Docker or Kubernetes, including GenAI, LLMs, DL, RL, AI agents, agentic workflows, or complex automation frameworks
2+ years of experience with LangChain, LangGraph, AutoGen, PydanticAI, CrewAI, or LlamaIndex
2+ years of experience working in cloud environments, including AWS and Azure, and evaluating architectural tradeoffs and designing robust service-based software applications for scalable use
Experience with MCP for tool integration and A2A for agent-to-agent collaboration
Experience with RAG architecture and knowledge graphs, including Neo4j or NebulaGraph
Experience fine-tuning LLMs or SLMs using Hugging Face, PEFT, or LoRA
Experience evaluating LLM performance and behavior through evaluations
Experience building observation layers for stakeholders, including Grafana, Langfuse, LangSmith, or Phoenix
Knowledge of modern software design patterns, including microservice design or edge computing
Ability to adapt in a rapidly changing environment and navigate ambiguity
TS/SCI clearance with a polygraph required
Bachelor’s degree
Master’s degree in a CS or AI field preferred
Doctorate degree in CS or Statistics a plus

Core Competencies

Demonstrates expertise in designing and implementing intelligent agent architectures, developing multi-agent systems, and fine-tuning machine learning models for production environments. Proficient in cloud technologies and evaluation frameworks to ensure reliability and performance of AI solutions.

Highest-signal resume keywords