AI Engineer (Agentic AI / AWS Bedrock)

ZealHire Inc.; Los Angeles (CA); Hybrid; USD 110,000 - 180,000; Full time

Job summary

ZealHire Inc. is seeking an experienced AI Engineer to design, deploy, and monitor production-grade agents using Claude Agent SDK and AWS Bedrock AgentCore.

You will translate complex business needs into reliable, observable AI workflows, balancing performance, cost, and security. Responsibilities include building scalable agent architectures, automating deployments with GitHub Actions, and implementing Langfuse for observability and evaluation.

Qualifications

• Hands-on AI engineer with production deployment experience.
• Proficient in Claude Agent SDK, AWS Bedrock AgentCore, Langfuse, GitHub Actions.
• Experience building observable, scalable enterprise AI solutions.

Responsibilities

• Design, develop, and deploy AI agents in Claude SDK and Python.
• Deploy agents on Amazon Bedrock AgentCore Runtime and integrate with data sources.
• Configure Langfuse for tracing, monitoring, and evaluation of agent traffic.
• Build CI/CD pipelines with GitHub Actions for automated deployments.
• Create AWS Step Functions workflows for document processing with Textract and Comprehend.
• Observe metrics, latency, and costs; troubleshoot production issues.

Skills

Claude Agent SDK

AWS Bedrock

AgentCore Runtime

Langfuse

GitHub Actions

Observability

LangChain

RAG

CI/CD

Python

Tools

Terraform

Docker

OpenSearch

Pinecone

FAISS

pgvector

Amazon Textract

Amazon Comprehend

LangGraph

LangChain

Job description

AI Engineer (Agentic AI / AWS Bedrock) | JPC-8849

Job Description – AI Engineer (Agentic AI / AWS Bedrock)

Duration: 3+ Months (Extension Possible)

Work Arrangement: Hybrid - 2 days onsite Locals Only

Visa: H1B/ /GC/GC-EAD/H4EAD (Need PP no for travel History) USC

LinkedIn should match the resume dates, projects and should be created before 2021 and have photograph and location mentioned

2 Manager references with LinkedIn

10 years of profile

Specialization: Agentic AI, AWS Bedrock AgentCore, Claude Agent SDK, Langfuse, AI Observability & Evaluation

Ideal Candidate Profile

A hands‑on AI Engineer who can take an agent from development through production deployment and ongoing evaluation. The candidate should be proficient in Claude Agent SDK, AWS Bedrock AgentCore, Langfuse, GitHub Actions, and continuous AI agent evaluation, with the ability to build reliable, scalable, and observable enterprise AI solutions.

Job Summary

We are seeking an experienced AI Engineer with strong hands‑on expertise in building, deploying, and monitoring production‑grade AI agents and Generative AI solutions using AWS technologies.

The ideal candidate will have experience developing AI agents using Claude Agent SDK, deploying them on Amazon Bedrock AgentCore Runtime, automating deployments through GitHub Actions, and implementing Langfuse for observability and continuous evaluation of agent traffic.

The role requires a strong combination of AI engineering, cloud deployment, data pipeline development, and LLM performance monitoring.

Key Responsibilities

1. Agentic AI Development

• Design, develop, and deploy AI agents using Claude Agent SDK and Python.
• Build intelligent, autonomous agents capable of executing complex workflows and interacting with external tools, APIs, and knowledge bases.
• Develop agent orchestration workflows with appropriate error handling, retry mechanisms, and guardrails.
• Integrate AI agents with enterprise applications and data sources.

2. AWS Bedrock & AgentCore

• Deploy and manage AI agents using Amazon Bedrock AgentCore Runtime.
• Develop scalable, secure, and production-ready agent architectures on AWS.
• Integrate agents with Amazon Bedrock foundation models and enterprise knowledge bases.
• Implement agent authentication, access controls, logging, and runtime monitoring.

3. Langfuse Deployment & AI Observability

• Deploy, configure, and maintain Langfuse for comprehensive LLM and agent observability.
• Integrate Langfuse with AI agents to capture traces, prompts, responses, tool calls, and execution metrics.
• Monitor agent performance, response latency, token consumption, and operational costs.
• Identify and troubleshoot production issues through distributed tracing and monitoring dashboards.
• Design and implement continuous evaluation frameworks for production AI agent traffic.
• Evaluate agent responses for accuracy, relevance, hallucinations, task completion, and tool execution quality.
• Develop automated evaluation pipelines using Langfuse, LLM-as-a-Judge, and custom evaluation metrics.
• Implement continuous feedback mechanisms to improve agent reliability and effectiveness.
• Establish quality benchmarks and detect agent performance regressions.
• Develop AWS Step Functions workflows integrating Amazon Textract and Amazon Comprehend for intelligent document processing.
• Build document ingestion, preprocessing, and data transformation pipelines.
• Implement vector database solutions, including document chunking, embedding generation, and vector indexing.
• Integrate AI agents with Retrieval-Augmented Generation (RAG) pipelines and enterprise knowledge bases.
• Optimize retrieval performance and contextual accuracy.

6. CI/CD & Deployment Automation

• Build and maintain CI/CD pipelines using GitHub Actions.
• Automate agent code builds, testing, deployment, and configuration management.
• Implement deployment workflows for Amazon Bedrock AgentCore Runtime.
• Integrate automated agent evaluations into CI/CD processes.
• Apply DevOps best practices for version control, release management, and production monitoring.

Required Technical Skills

• Evaluation: Continuous agent evaluation, LLM-as-a-Judge, evaluation metrics and automated testing.
• RAG: Vector databases, embeddings, chunking strategies, indexing, knowledge base integrations.
• Cloud: AWS architecture, IAM, CloudWatch, security, and deployment practices.

Good-to-Have Skills

• Experience with LangChain, LangGraph, or other agent orchestration frameworks.
• Experience with RAGAS, DeepEval, or similar LLM evaluation frameworks.
• Familiarity with Amazon OpenSearch, Pinecone, FAISS, or pgvector.
• Experience with Docker, Terraform, or infrastructure as code.
• Knowledge of Model Context Protocol (MCP).
• Experience with prompt engineering, guardrails, and AI governance.
• Experience deploying enterprise Generative AI solutions in production environments.

$000,000 – $000,000 Salary range is not shown on the candidate portal