Senior GenAI Developer

Senior Generative AI Developer (LLMs | AWS) Hybrid, Houston TX $70-75/Hour Seeking a Senior Generative AI Developer (LLMs | AWS) with hands-on experience designing, optimizing, and scaling LLM architectures, including cost control, performance tuning, and efficient inference. Key Responsibilities Design, develop, and deploy LLM-based applications on AWS using services such as Amazon Bedrock, SageMaker, Lambda, ECS/EKS, and API Gateway. Architect scalable and cost-efficient GenAI systems leveraging auto-scaling, serverless, and containerized workloads. Optimize LLM inference and training costs using techniques such as model selection, prompt optimization, batching, caching, and fine-tuning on SageMaker. Build and maintain RAG pipelines using S3, OpenSearch, Aurora/DynamoDB, and vector databases. Implement observability and monitoring for LLM workloads using CloudWatch, Datadog, X-Ray, and OpenTelemetry, tracking latency, token usage, and cost. Ensure security and compliance using IAM, VPC, KMS, Secrets Manager, and AWS best practices. Evaluate and integrate open-source and managed LLMs (Bedrock, custom models on SageMaker) based on performance and cost. Perform capacity planning and performance benchmarking for LLM applications. Collaborate with cross-functional teams to productionize and scale GenAI solutions. Provide technical leadership, code reviews, and mentorship to engineering teams. Required Skills & Qualifications Bachelor’s or Master’s degree in Computer Science, Engineering, AI/ML, or a related field. 6+ years of software development experience, with 4+ years AWS and 2+ years working on AI/ML or Generative AI systems. Proven, hands-on experience designing, developing, and deploying LLM-based applications in production. Strong expertise in AWS cloud services, including Amazon Bedrock, SageMaker, Lambda, ECS/EKS, S3, API Gateway, and CloudWatch. Deep understanding of LLM architectures, prompt engineering, fine-tuning techniques, and RAG-based systems. Demonstrated experience building scalable, high-availability GenAI systems. Strong knowledge of cost optimization strategies for LLM workloads (token efficiency, batching, caching, model selection). Proficiency in Python and familiarity with GenAI frameworks such as LangChain, LlamaIndex, and Hugging Face. Experience with containerization and orchestration (Docker, Kubernetes/EKS). Hands-on experience with observability and monitoring tools (CloudWatch, Datadog, OpenTelemetry). Solid understanding of cloud security best practices (IAM, VPC, KMS, Secrets Manager). Experience mentoring junior developers and providing technical leadership. Excellent problem-solving, communication, and collaboration skills. Brooksource provides equal employment opportunities (EEO) to all employees and applicants for employment without regard to race, color, religion, national origin, age, sex, citizenship, disability, genetic information, gender, sexual orientation, gender identity, marital status, amnesty or status as a covered veteran in accordance with applicable federal, state, and local laws. Pay: $70.00 - $75.00 per hour Expected hours: 40.0 per week Benefits: Dental insurance Health insurance Vision insurance Work Location: Hybrid remote in Houston, TX 77015