Information Technology_USA - USA_Engineer

Key Responsibilities: Design, build, deploy, secure, and operate production-ready AI agents using the AWS Strands Agents SDK and Amazon Bedrock AgentCore. Preferred Qualifications Experience with OpenSearch, pgvector, Pinecone, Redis, or comparable vector technologies, plus hybrid search, reranking, and advanced RAG patterns.

Job Title : AI Platform Engineer
Location: Woodland Hills, CA (Onsite)
Duration: 6 Months
 
Salary Range: $50.00 - $52.00/Hour on W2 (Without Benefits).
Applicants must be willing to work on W2.
 
Job Description:

• We are seeking an AI Platform Engineer to design, build, deploy, secure, and operate production-ready AI agents and reusable AI platform components on AWS.

Key Responsibilities:

• Design, build, deploy, secure, and operate production-ready AI agents using the AWS Strands Agents SDK and Amazon Bedrock AgentCore.
• Architect reusable agent platform components, APIs, deployment patterns, and controls for scalability, availability, observability, governance, and cost efficiency.
• Build AWS Lambda and AWS Glue-based ingestion pipelines for parsing, metadata enrichment, chunking, embeddings, vector indexing, synchronization, and data-quality validation.
• Design Amazon Bedrock Knowledge Base and custom RAG solutions, selecting and tuning chunking, embedding, vector store, metadata, retrieval, reranking, and HNSW/IVF index strategies.
• Integrate automated retrieval, response-quality, regression, and safety evaluation into CI/CD release gates.
• Maintain a governed, versioned prompt library and develop platform services, automation, and integrations in Python and JavaScript.
• Implement monitoring, tracing, logging, alerting, security, and troubleshooting across agents and data pipelines.
• Collaborate with product, data, security, DevOps, and application teams to deliver reliable, maintainable AI solutions.
• Apply AIOps capabilities, including ignio AIOps, to support AI platform operations, monitoring, analytics, insights, and troubleshooting.
• Apply Data Analytics & Insights experience to support scalable AI platform operations and data-driven engineering decisions.

Required Qualifications:

• 10+ years of software, cloud, data, or platform engineering experience.
• 3+ years designing AI/ML or Generative AI solutions on AWS.
• 7+ years of Data Analytics & Insights experience.
• Hands-on experience building agents with the AWS Strands Agents SDK and deploying them through Amazon Bedrock AgentCore.
• Architecture-level knowledge of RAG, Bedrock Knowledge Bases, chunking, embedding models, vector stores, semantic retrieval, metadata filtering, and evaluation.
• Experience building scalable ingestion, embedding, indexing, reprocessing, and data-quality pipelines using AWS Lambda and Glue.
• Practical experience configuring and tuning HNSW, IVF, or comparable approximate nearest-neighbor indexes.
• Experience integrating AI and retrieval evaluation, regression checks, safety tests, and quality gates into CI/CD.
• Proficiency in prompt engineering, testing, versioning, and shared prompt-library design.
• Strong Python and JavaScript skills, including API integration, automated testing, packaging, debugging, and maintainable design.
• Knowledge of AWS IAM, networking, encryption, secrets, monitoring, least-privilege security, architecture documentation, and production runbooks.
• Experience with ignio AIOps.

Preferred Qualifications

• Experience with OpenSearch, pgvector, Pinecone, Redis, or comparable vector technologies, plus hybrid search, reranking, and advanced RAG patterns.
• Experience with infrastructure as code, containers, cloud-native CI/CD, and reusable APIs, SDKs, or engineering templates.
• Knowledge of LLM observability, hallucination analysis, prompt-injection defenses, guardrails, and responsible AI controls.
• Bachelor’s degree in Computer Science, Engineering, Information Technology, or a related field, or equivalent practical experience.