Full Stack Engineer (Node.js, Python)

About the Company
The organization is expanding its AI capabilities through an AI Center of Excellence focused on developing and deploying practical AI solutions. The team works across cloud infrastructure, AI frameworks, and software engineering to build intelligent systems that address business needs.
About the Role
The organization is seeking an AI Full Stack Engineer to design, develop, and deploy AI agents and applications powered by Large Language Models (LLMs) and Small Language Models (SLMs). This hands-on individual contributor role covers the full development lifecycle, from prototyping and agent orchestration to production deployment and ongoing monitoring.
You will work with AWS Bedrock, Python, Node.js, and agentic AI frameworks to build autonomous, multi-step, and tool-using agents. The role also involves model evaluation, observability, responsible AI practices, and collaboration with product and engineering teams to turn business requirements into reliable AI-powered features.
This is a long-term, full-time contract engagement. The position is remote, with some travel to Atlanta, Georgia. Candidates must be legally eligible to work where they live and submit their resumes in English.
Key Responsibilities
Design and develop autonomous, multi-step, and tool-using AI agents using AWS Bedrock and agentic AI frameworks.
Build, fine-tune, and integrate LLMs and SLMs into production workflows.
Develop backend services, APIs, and agent orchestration layers using Python and Node.js.
Use AWS Bedrock foundation models, Knowledge Bases, and Agents for Bedrock to build and deploy AI solutions.
Implement agent monitoring, observability, and evaluation pipelines using Fiddler AI or comparable platforms.
Define and track agent performance metrics, including accuracy, latency, hallucination rate, tool-call success, and cost.
Collaborate with product and engineering teams to translate business requirements into reliable AI-powered features.
Establish and follow best practices for responsible AI, prompt engineering, model evaluation, and agent safety.
Evaluate emerging AI models, frameworks, and tools to identify opportunities for improvement.
Contribute to technical documentation, architecture reviews, and knowledge sharing across the team.
Take ownership of AI features from initial development through production deployment and ongoing troubleshooting.
Required Qualifications
At least three years of professional software engineering experience, including hands-on development of AI- or LLM-powered applications.
Practical experience building and deploying models and AI agents on AWS Bedrock, including foundation model access, Knowledge Bases, and Agents for Bedrock.
Familiarity with AWS services such as Lambda, S3, IAM, and API Gateway.
Hands-on experience developing autonomous agents, tool-calling agents, ReAct or plan-and-execute workflows, and multi-agent orchestration.
Experience with agentic frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or AWS Bedrock Agents.
Strong understanding of agent memory, context management, and tool use.
Proficiency in Python for agent logic, machine learning pipelines, data processing, and scripting.
Proficiency in Node.js for API development, backend services, and agent integration.
Practical experience working with LLMs such as Claude, GPT-4, Llama, or Mistral, and SLMs such as Phi-3, Gemma, or Mistral 7B.
Knowledge of prompt engineering, few-shot learning, Retrieval-Augmented Generation (RAG), and fine-tuning workflows.
Experience with Fiddler AI or comparable model and agent monitoring tools, such as LangSmith, Arize, Weights & Biases, or Helicone.
Ability to evaluate agent performance and monitor quality, latency, reliability, and cost.
Preferred Qualifications / Requirements
Experience with vector databases such as Pinecone, pgvector, OpenSearch, or Weaviate for semantic search and RAG pipelines.
Familiarity with MLOps practices, including model CI/CD, model versioning, and A/B evaluation.
Exposure to multimodal models combining vision and language.
Previous experience working on an AI product or platform team at scale.
AWS certifications, such as AWS Certified Machine Learning – Specialty.
A practical, hands-on approach to software development, production debugging, and end-to-end feature ownership.
Strong communication skills, including the ability to explain complex AI behavior to non-technical stakeholders.
Location and Work Arrangement
Remote position, with some travel to Atlanta, Georgia.
Long-term, full-time contract engagement.
Candidates must be legally eligible to work where they live.
Resume must be submitted in English.

Work arrangement
Yes