Technical Architect – ML, GenAI

This is a fully remote position, open to applicants in United States.

📋 Description

• Design and develop enterprise-level Generative AI solutions utilizing AWS Bedrock and AgentCore.

• Establish architecture for LLM-based applications, encompassing RAG pipelines and agentic workflows.

• Create and manage agentic AI workflows that support multi-step reasoning, tool utilization, and task automation.

• Construct and oversee RAG pipelines that incorporate embeddings, retrieval methods, and vector databases.

• Integrate LLM functionalities into corporate applications via APIs and backend services.

• Devise and enhance prompt engineering techniques.

• Collaborate with both structured and unstructured data sources for knowledge-driven AI applications.

• Assess, monitor, and refine models for latency, cost, and response quality.

• Partner with application, data, and platform teams for complete solution delivery.

• Establish security, governance, and responsible AI best practices.

• Diagnose and resolve production GenAI system challenges.

• Offer technical guidance and mentor team members while maintaining a hands-on approach.

⛳️ Requirements

• 8+ years of relevant practical technical experience in implementing and developing cloud ML solutions on AWS.

• Practical experience with AWS services, including SageMaker and Bedrock.

• Familiarity with AWS SageMaker training jobs and real-time as well as batch applications.

• Experience in designing and executing agentic AI architectures using LangChain, Strand Agents, or comparable frameworks.

• Hands-on experience with Amazon AgentCore, including agent memory management, tool registry, and observability.

• Proficient in architecting and deploying scalable AI solutions using Lambda, Bedrock, Step Functions, S3, API Gateway, and SageMaker.

• Knowledge of LLM APIs, such as Claude, Nova, and other external providers.

• Practical experience in fine-tuning or optimizing LLMs.

• Understanding of LLM tool use, prompt templating, and context management.

• Strong knowledge of vector databases, indexing, embeddings, similarity search, and RAG integration.

• Experience in evaluating and optimizing LLM zero-shot and few-shot capabilities, fine-tuning hyperparameters, task generalization, and model interpretability.

• Background in developing and maintaining Model Context Protocol implementations.

• Familiarity with workflow orchestration tools such as Airflow, Step Functions, SageMaker Pipelines, or Kubeflow.

• Experience in implementing secure, scalable APIs and integrating third-party data sources and tools.

• Ability to collaborate effectively with developers, QA, project managers, and other stakeholders.

• Knowledge of deep learning concepts including Transformers, BERT, attention models, tokenization, and embeddings.

• Nice to have: software development experience along with exposure to frontend/backend frameworks and communication protocols.

• Nice to have: experience in Infrastructure as Code and CI/CD pipelines.

• Nice to have: familiarity with NLP concepts including syntactic/semantic analysis and NER.

🏝️ Benefits

• A culture founded on transparency, diversity, integrity, and opportunities for learning and growth.

• An environment that fosters innovation and supports both professional and personal development.