Senior Engineer, AI/ML

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

📋 Description

• Develop production agents utilizing Strands/LangGraph on AWS Bedrock AgentCore, encompassing agent logic, tool orchestration, and multi-agent workflows.

• Deploy agents on the AgentCore Runtime with Memory, Identity, and Gateway functionalities.

• Create framework-agnostic Python tools, MCP servers, and AgentCore Gateway targets to ensure the secure calling of production APIs.

• Design offline and online evaluation pipelines along with LLM-as-judge CI/CD gates.

• Establish approval gates and rollback mechanisms for safe failure management.

• Oversee per-agent costs and latency through diligent tracking and multi-model routing.

• Deliver production observability utilizing AgentCore session tracing, OpenTelemetry, and CloudWatch dashboards.

• Operate within predefined platform architectural patterns to provide agentic frameworks, AWS serverless core, MCP/tool design, and observability solutions.

• Familiarize yourself with platform architecture, existing agents, integration surfaces, and dealer workflows.

• Successfully launch a first tool integration to production within the initial month.

• Take ownership of end-to-end agent workflows from design to production in months 2–3.

• Independently deploy new agents and tools with observability and cost tracking starting from month 4 onward.

⛳️ Requirements

• A minimum of 5 years of software engineering experience, including practical production experience in developing LLM agents within a code-first framework.

• Proven hands-on production experience with LLM agent frameworks like Strands Agents, LangGraph, Google ADK, OpenAI Agents SDK, or similar frameworks.

• Business-minded judgment with a focus on addressing customer challenges and delivering value.

• Proficient in Python programming.

• Capability to read and contribute to Java (Spring Boot) services.

• Practical experience with AWS serverless technologies: Lambda, EventBridge, DynamoDB, and Step Functions.

• Experience in prompt engineering, tool/function-calling design, and assessing LLM output quality in a production environment.

• A strong inclination towards a hands-on development role, reflected in delivered code.

• Strongly preferred: Experience with Strands Agents and/or AgentCore Runtime, LLM-as-judge, agent-to-agent orchestration, and agent governance.

• Strongly preferred: Direct production experience with MCP servers.

• Strongly preferred: Experience in production observability using OpenTelemetry and CloudWatch.

• Nice to have: Experience in automotive, fintech, or multi-tenant marketplace platforms.

• Nice to have: Familiarity with Bedrock Guardrails, LLM-as-judge evaluation, model cost/latency optimization, and multi-agent orchestration patterns.

• Nice to have: Experience with data pipelines such as Glue/Athena or ETL/data lake tools.

🏝️ Benefits

• Comprehensive medical, dental, and vision coverage.

• Employer-sponsored short-term and long-term disability and life insurance.

• 401k matching plan.

• Unlimited paid time off, including 10 paid holidays.

• Genuine ownership of a critical AI surface — your roadmap, your architectural decisions, and your metrics.