Adbakx LLC
Role: AI Expert Developer (Full Stack / AWS)
Location: Provo, UT
Employment Type: Contract. Preferred onsite/hybrid
About the Role
The client is looking for a highly skilled AI Expert Developer with strong full stack development capabilities and deep expertise in cloud-native AI/ML solutions. This role bridges applied AI/LLM development with enterprise-grade web/backend engineering. You will be responsible for designing, developing, and deploying AI-powered applications and services across our AWS environment, ensuring scalability, security, and performance.
Responsibilities Design, build, and deploy AI-powered applications leveraging LLMs, vector databases, and graph databases.
Develop and maintain full stack web applications using Node.js, Python, and Java (optional but preferred).
Architect, implement, and manage serverless and containerized solutions using the AWS stack (Lambda, ECS, EKS, S3, API Gateway, DynamoDB, RDS, Step Functions, Bedrock, SageMaker, etc.).
Integrate and fine‑tune large language models (open-source and proprietary) and embed them into production systems.
Implement retrieval‑augmented generation (RAG) patterns, prompt engineering, guardrails, and vector database integrations (Pinecone, Weaviate, Redis, Neo4j, Amazon Neptune).
Apply software architecture best practices including hexagonal architecture, event‑driven patterns, and domain‑driven design.
Collaborate with enterprise architects and solution teams to align AI systems with business capabilities and platform engineering standards.
Optimize backend performance, implement APIs and microservices, and ensure secure integrations with internal and third‑party systems.
Monitor, evaluate, and continuously improve AI models and pipelines for reliability, interpretability, and cost efficiency.
Mentor team members on AI concepts, coding best practices, and architectural design.
Required Skills & Experience Programming: Strong expertise in Node.js and Python; proficiency with Java is a plus.
Cloud: Hands‑on experience with the AWS ecosystem (EC2, Lambda, S3, API Gateway, DynamoDB, RDS, Step Functions, CloudFormation/CDK, Bedrock, SageMaker).
AI/ML: Experience with LLMs, embeddings, prompt design, fine‑tuning, and RAG architectures.
Databases: Deep knowledge of vector databases (Pinecone, Weaviate, FAISS, Redis) and graph databases (Neo4j, Neptune).
Architecture: Strong grounding in design patterns, integration strategies, and microservices/serverless architectures.
Frontend: Solid skills in React, Next.js, or similar frameworks for building modern, scalable UIs.
DevOps: Familiarity with CI/CD pipelines, Docker, Kubernetes (EKS), monitoring (CloudWatch, Grafana, Prometheus).
Security & Compliance: Knowledge of IAM, VPC, KMS, Cognito, and security best practices in the cloud.
Collaboration: Ability to partner with architects, engineers, and business stakeholders to translate requirements into working AI‑enabled solutions.
Preferred Skills Experience with LangChain, LlamaIndex, Hugging Face Transformers, OpenAI/Anthropic APIs.
Familiarity with event‑driven architecture (AWS EventBridge (preferred), Kafka, Kinesis).
Experience in multi‑agent AI systems, orchestration frameworks, and workflow automation (e.g., Airflow, n8n, Step Functions).
Understanding of data engineering pipelines, ETL/ELT, and integration with data lakes/warehouses.
Contributions to open‑source AI/ML projects or publications.
#J-18808-Ljbffr
Responsibilities Design, build, and deploy AI-powered applications leveraging LLMs, vector databases, and graph databases.
Develop and maintain full stack web applications using Node.js, Python, and Java (optional but preferred).
Architect, implement, and manage serverless and containerized solutions using the AWS stack (Lambda, ECS, EKS, S3, API Gateway, DynamoDB, RDS, Step Functions, Bedrock, SageMaker, etc.).
Integrate and fine‑tune large language models (open-source and proprietary) and embed them into production systems.
Implement retrieval‑augmented generation (RAG) patterns, prompt engineering, guardrails, and vector database integrations (Pinecone, Weaviate, Redis, Neo4j, Amazon Neptune).
Apply software architecture best practices including hexagonal architecture, event‑driven patterns, and domain‑driven design.
Collaborate with enterprise architects and solution teams to align AI systems with business capabilities and platform engineering standards.
Optimize backend performance, implement APIs and microservices, and ensure secure integrations with internal and third‑party systems.
Monitor, evaluate, and continuously improve AI models and pipelines for reliability, interpretability, and cost efficiency.
Mentor team members on AI concepts, coding best practices, and architectural design.
Required Skills & Experience Programming: Strong expertise in Node.js and Python; proficiency with Java is a plus.
Cloud: Hands‑on experience with the AWS ecosystem (EC2, Lambda, S3, API Gateway, DynamoDB, RDS, Step Functions, CloudFormation/CDK, Bedrock, SageMaker).
AI/ML: Experience with LLMs, embeddings, prompt design, fine‑tuning, and RAG architectures.
Databases: Deep knowledge of vector databases (Pinecone, Weaviate, FAISS, Redis) and graph databases (Neo4j, Neptune).
Architecture: Strong grounding in design patterns, integration strategies, and microservices/serverless architectures.
Frontend: Solid skills in React, Next.js, or similar frameworks for building modern, scalable UIs.
DevOps: Familiarity with CI/CD pipelines, Docker, Kubernetes (EKS), monitoring (CloudWatch, Grafana, Prometheus).
Security & Compliance: Knowledge of IAM, VPC, KMS, Cognito, and security best practices in the cloud.
Collaboration: Ability to partner with architects, engineers, and business stakeholders to translate requirements into working AI‑enabled solutions.
Preferred Skills Experience with LangChain, LlamaIndex, Hugging Face Transformers, OpenAI/Anthropic APIs.
Familiarity with event‑driven architecture (AWS EventBridge (preferred), Kafka, Kinesis).
Experience in multi‑agent AI systems, orchestration frameworks, and workflow automation (e.g., Airflow, n8n, Step Functions).
Understanding of data engineering pipelines, ETL/ELT, and integration with data lakes/warehouses.
Contributions to open‑source AI/ML projects or publications.
#J-18808-Ljbffr