About the Role

We are seeking a highly skilled Generative AI Engineer to design, develop, and deploy advanced AI-powered applications leveraging Large Language Models (LLMs), agent frameworks, and Retrieval-Augmented Generation (RAG) architectures. The ideal candidate will have hands-on experience building scalable AI systems, microservices, APIs, and multi-agent workflows while ensuring security, reliability, and performance.

This role will collaborate closely with software engineers, data scientists, architects, and product teams to deliver enterprise-grade AI solutions.

Responsibilities

AI Agent Development

• Design and implement single-agent and multi-agent systems using frameworks such as LangGraph, Claude Agent SDK, LangChain, Semantic Kernel, CrewAI, AutoGen, or similar.
• Develop agent architectures utilizing planner, executor, critic, router, and orchestrator patterns.
• Enable agent collaboration and coordination across distributed workflows.
• Implement tool calling, structured outputs, function calling, and streaming capabilities.

RAG & Knowledge Systems

• Design and develop Retrieval-Augmented Generation (RAG) pipelines.
• Build ingestion, chunking, embedding, indexing, and retrieval workflows.
• Implement vector search solutions using pgvector, FAISS, OpenSearch, or equivalent technologies.
• Develop citation generation and response grounding mechanisms.
• Integrate Bedrock Titan embeddings and modern retrieval strategies including hybrid search.

Backend & Platform Development

• Build secure, scalable APIs and microservices using Python/FastAPI or Node.js/TypeScript.
• Develop asynchronous services with robust validation using Pydantic.
• Integrate AI services with PostgreSQL, S3, and other enterprise data stores.
• Design and implement MCP integrations, tool schemas, idempotent operations, and resilient error handling.
• Develop containerized applications using Docker and CI/CD best practices.

Evaluation & Quality

• Build evaluation frameworks including golden datasets, regression testing, LLM-as-a-Judge methodologies, and automated benchmarking.
• Monitor model accuracy, hallucination rates, response quality, latency, and cost.
• Implement observability, tracing, and monitoring solutions for AI systems.
• Drive continuous improvements in reliability, scalability, and performance.

Security & Governance

• Implement guardrails including input/output validation and schema enforcement.
• Develop prompt-injection defenses and content safety controls.
• Apply rate limiting, authentication, authorization, and secure API design principles.
• Ensure adherence to enterprise AI governance and compliance requirements.

Collaboration

• Participate in architecture reviews, technical design discussions, and code reviews.
• Partner with cross-functional teams to translate business requirements into scalable AI solutions.
• Take ownership of code quality, documentation, and engineering excellence.

Minimum Qualifications

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, Software Engineering, or a related technical field.
• 3–8 years of professional experience in software engineering, data engineering, or AI/ML development.
• Hands-on experience developing Generative AI, LLM-powered, or AI agent applications.
• Strong programming experience in Python (FastAPI, AsyncIO, Pydantic) and/or Node.js/TypeScript.
• Experience designing and developing APIs, microservices, and distributed systems.
• Practical experience with LLM function calling, tool integrations, structured outputs, and streaming responses.
• Experience implementing RAG solutions using vector databases and retrieval technologies.
• Familiarity with Git, CI/CD pipelines, Docker, and cloud platforms (AWS preferred).

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.