Location: Wilmington, DE
Salary: $58.00 USD Hourly - $63.00 USD Hourly
Description: Job Description - AI / Software Engineer (Contingent Assignment)Location: Wilmington, DE (Hybrid - 3 days onsite)
Duration: 12-month contract, potential extension
Start Date: ASAP
OverviewIn this contingent role, you will contribute to
end-to-end AI engineering, supporting initiatives across large-scale software platforms. You will design, build, and optimize generative AI systems, LLM-powered agentic workflows, RAG pipelines, and cloud-native infrastructure. This position requires strong technical judgment, hands-on engineering experience, and the ability to collaborate across cross-functional software and AI teams.
Key ResponsibilitiesGenerative & Agentic AI Engineering- Develop and optimize LLM-driven autonomous agents, multi-agent systems, and tool-augmented workflows.
- Build Model Context Protocol (MCP) servers and structured context-management frameworks.
- Architect and implement RAG pipelines including embeddings, vector search, retrieval layers, grounding strategies, and prompt-engineering frameworks.
- Implement LLM function calling, multi-step orchestration, safety guardrails, evaluation frameworks, and quality controls.
Python & Enterprise AI Engineering- Build high-performance Python microservices and AI APIs using FastAPI, Flask, LangChain, LlamaIndex, and MCP SDKs.
- Engineer distributed AI systems for large-scale inference, retrieval, and multi-agent orchestration.
Enterprise Engineering Ecosystem- Use tools including Jupyter Notebooks, Tachyon, and enterprise GenAI platforms for experimentation and model evaluation.
- Leverage GitHub Copilot / DevX to accelerate development and support modern DevSecOps workflows.
- Contribute reusable AI patterns, enterprise accelerators, and responsible AI guardrails.
Cloud & Platform Engineering- Deploy and operate AI solutions on Google Cloud Platform (Google Cloud Platform): GKE, Vertex AI, Cloud Run, IAM, and related services.
- Containerize and orchestrate AI workloads using Red Hat OpenShift and enterprise Kubernetes platforms.
- Build and manage CI/CD pipelines aligned with DevOps and enterprise governance standards.
Data, Retrieval & Integration- Work with vector databases such as MongoDB Atlas Vector Search, Chroma, Pinecone, Redis, pgVector, and others.
- Build secure and scalable retrieval layers, embedding pipelines, and long-term memory modules for agentic workflows.
Architecture, Governance & Delivery- Participate in architecture reviews and support responsible AI and compliance frameworks.
- Ensure adherence to risk, security, and regulatory standards.
- Lead POCs, engineering improvements, and innovation workstreams with minimal oversight.
Required Qualifications- Bachelor's or Master's degree in Computer Science, Computer Engineering, or related technical field.
- 5+ years of professional Python development experience, including automation, APIs, async programming, and microservices.
- 3+ years of hands-on experience building LLM, generative AI, or agentic AI systems.
- Proven experience with RAG pipelines, embeddings, vector search, and LLM orchestration.
- Experience deploying AI systems on Google Cloud Platform and Kubernetes/OpenShift.
- Proficiency with Jupyter, Tachyon, GitHub Copilot, and modern CI/CD + DevOps environments.
- Ability to operate independently and drive AI innovation.
- 4+ years of software engineering experience, or equivalent through work, consulting, training, military service, or education.
Desired Qualifications- Familiarity with LangChain, LlamaIndex, and APIs for OpenAI, Google Gemini, or similar model families.
- Experience with observability tools: Grafana, Prometheus, Cloud Logging, etc.
- Strong communication and ability to collaborate with both technical and business stakeholders.
Additional InformationSkills Focus:- Python, automation, machine learning, generative AI, MCP
- Strong hands-on engineering with modern LLM ecosystems
Work Model:- Hybrid; aligned to U.S. Eastern Time business hours.
By providing your phone number, you consent to: (1) receive automated text messages and calls from the Judge Group, Inc. and its affiliates (collectively "Judge") to such phone number regarding job opportunities, your job application, and for other related purposes. Message & data rates apply and message frequency may vary. Consistent with Judge's Privacy Policy, information obtained from your consent will not be shared with third parties for marketing/promotional purposes. Reply STOP to opt out of receiving telephone calls and text messages from Judge and HELP for help.
Contact: This job and many more are available through The Judge Group. Please apply with us today! 
Never miss an opportunity! Create an alert based on the job you applied for.