Technical Architect – ML, GenAI

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

📋 Description

• Design and implement Generative AI solutions utilizing AWS Bedrock and Agentcore.

• Define the architecture for applications based on Large Language Models (LLMs), encompassing Retrieval-Augmented Generation (RAG) pipelines and agentic workflows.

• Develop and orchestrate workflows for agentic AI focused on multi-step reasoning, tool utilization, and task automation.

• Construct and manage RAG pipelines, embeddings, retrieval mechanisms, and vector databases.

• Integrate LLM capabilities into enterprise applications via APIs and backend services.

• Design and refine strategies for prompt engineering.

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

• Evaluate, monitor, and optimize models considering latency, cost, and response quality.

• Work alongside application, data, and platform teams to ensure complete solution delivery.

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

• Diagnose and resolve issues within production Generative AI systems.

• Provide technical leadership and mentor team members while maintaining a hands-on approach.

⛳️ Requirements

• Over 8 years of relevant hands-on technical experience in implementing and developing cloud-based machine learning solutions on AWS.

• Practical experience with various AWS services.

• Demonstrated expertise with AWS SageMaker and Bedrock, including working with diverse data sources, training jobs, and both real-time and batch applications.

• Experience in designing and implementing agentic AI architectures using frameworks like LangChain and Strand Agents.

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

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

• Proficient in LLM APIs such as Claude, Nova, and other third-party providers, including API integration and the orchestration of multiple models.

• Practical experience in fine-tuning or optimizing LLMs.

• Familiarity with LLM tool usage, prompt templating, and context management.

• Strong expertise in vector databases, indexing strategies, embedding generation, similarity search, and RAG integration.

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

• Experience in developing and maintaining implementations of Model Context Protocol.

• Familiarity with at least one workflow orchestration tool, such as Airflow, Step Functions, SageMaker Pipelines, or Kubeflow.

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

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

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

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

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

• Nice to have: understanding of NLP concepts including syntactic/semantic analysis and Named Entity Recognition (NER).

🏝️ Benefits

• Opportunities for learning and professional growth.

• Chance to engage with colleagues from diverse experiences and backgrounds worldwide.

• A diverse and hybrid work culture (company-wide culture statement).