AI Engineer

Remote Role

Fully Remote (W2 Contract)

Compensation: $60 - $85 per hour

ABOUT THE ROLE

Our client is seeking a highly skilled and strategic AI Engineer to lead and accelerate AI initiatives, with a primary focus on Retrieval-Augmented Generation (RAG) and Multi-Agent architectures. This fully remote W2 contract role offers competitive hourly pay, benefits, and paid time off. As the driving force behind designing, developing, and deploying cutting-edge AI solutions, you will collaborate closely with technical leadership and engineering teams to architect intelligent, scalable, and highly performant AI applications from proof-of-concept to enterprise-grade production. You will be responsible for architecting robust RAG pipelines, optimizing data ingestion and chunking strategies, establishing rigorous evaluation frameworks, and integrating AI models into backend services and user interfaces. The role leverages cloud-native services for secure hosting, scaling, and management of LLMs, vector databases, and agentic workflows. Brooksource, Medasource, and Calculated Hire are part of the Eight Eleven Group family of companies and operate under Eight Eleven Group, LLC. All employees receive the same benefits, policies, and terms of employment. We are committed to creating an inclusive environment for all employees and applicants, and offer comprehensive benefits including medical, dental, vision, HSA, FSA, supplemental coverage, 401k with company match, paid time off, sick time, paid company holidays, and Employee Assistance Program (EAP) services.

WHAT YOU'LL DO

• Design, architect, and implement robust Retrieval-Augmented Generation (RAG) pipelines and collaborative multi-agent systems to solve complex business problems
• Develop and optimize advanced data ingestion pipelines, applying sophisticated document parsing and chunking strategies (semantic, recursive, context-aware) to maximize retrieval accuracy and relevance
• Establish rigorous evaluation frameworks and techniques (using tools like RAGAS, TruLens, or custom metrics) to continuously assess and improve hallucination rates, context precision, and overall model performance
• Act as a full-lifecycle engineer, building AI models and integrating them into reliable backend services and functional user interfaces
• Leverage cloud-native services to securely host, scale, and manage LLMs, vector databases, and agentic workflows
• Collaborate with technical leadership and engineering teams to move AI solutions from proof-of-concept to enterprise-grade production
• Utilize programming expertise in Python for backend development, data processing, and AI/ML orchestration
• Apply hands-on experience with LLM orchestration frameworks and advanced retrieval techniques (Hybrid search, query routing, re-ranking)
• Support cloud deployment and DevOps processes, including containerization (Docker, Kubernetes), CI/CD pipelines, and infrastructure-as-code (Terraform)
• Contribute to building seamless APIs and front-end interfaces for AI solutions using modern web development frameworks (FastAPI, Flask, React, Vue, etc.)

WHAT YOU BRING

• Deep proficiency in Python for backend development, data processing, and AI/ML orchestration
• Extensive hands-on experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex, AutoGen, CrewAI, LangGraph)
• Proven track record of building production-level RAG systems, including embedding generation, vector database management (e.g., Pinecone, Weaviate, Milvus, pgvector), and advanced retrieval techniques (Hybrid search, query routing, re-ranking)
• Strong understanding of LLM evaluation techniques, prompt engineering methodologies, and continuous improvement cycles for generative outputs
• Hands-on experience with Google Cloud Platform (GCP), specifically utilizing Vertex AI for model hosting, fine-tuning, and deployment (preferred)
• Familiarity with modern web development frameworks (FastAPI, Flask, React, Vue, etc.) to build APIs and front-end interfaces for AI solutions (preferred)
• Broad cloud engineering skills, including containerization (Docker, Kubernetes), CI/CD pipelines, and infrastructure-as-code (Terraform) (preferred)

WHAT'S IN IT FOR YOU

• Competitive medical, dental, vision, Health Savings Account, Dependent Care FSA, and supplemental coverage options
• 401k plan with company match, fully vested after eligibility
• Paid time off, sick time, and paid company holidays
• Employee Assistance Program (EAP) offering virtual counseling, financial services, legal services, life coaching, and more
• Inclusive work environment with equal opportunity employment practices

#LI-AH2