Senior Engineer, AI/ML

TriSearch; Denver (CO); Hybrid; USD 160.000 - 190.000; Vollzeit

Benefits dieser Stelle

Health coverage

Flexible work options (Hybrid in US)

401(k) match

Unlimited PTO

Disability insurance

Life Insurance

BetterHelp mental health support

On-site gym and stocked kitchen (in DC

Zusammenfassung

TriSearch is seeking a Senior Engineer, AI/ML in Denver or fully remote within the United States. You will design, build, deploy, and maintain production AI agents and multi-agent workflows using code-first frameworks and AWS Bedrock AgentCore.

You will develop Python tools, MCP servers, and secure integrations to connect AI agents with APIs, cloud services, and business systems, while implementing guardrails, testing, and evaluation for reliable, safe operation.

Qualifikationen

• 5+ years of professional software engineering experience, including hands-on experience building and operating production LLM-based AI agents using a code-first framework.
• Strong Python development skills and the ability to read, understand, and contribute to Java/Spring Boot services.
• Hands-on experience with AWS serverless technologies, such as Lambda, EventBridge, DynamoDB, S3, and Step Functions.
• Experience with prompt engineering, tool or function calling, and evaluating the quality and reliability of LLM outputs.
• Understanding of production software engineering principles, including testing, deployment, monitoring, security, and error handling.
• Demonstrated ability to take ownership of technical projects and deliver working solutions.
• Strong problem-solving skills and sound business judgment, with the ability to evaluate the value, complexity, and trade-offs of potential solutions.
• Comfort working in a fast-paced, evolving environment where priorities may change and engineers are expected to take initiative.

Aufgaben

• Design, build, deploy, and maintain production AI agents and multi-agent workflows using code-first frameworks and AWS Bedrock AgentCore.
• Develop reusable Python tools, MCP servers, and secure integrations that connect AI agents to APIs, cloud services, and business systems.
• Implement prompt engineering, automated testing, AI evaluation, guardrails, and approval processes to ensure agent accuracy, reliability, and safe operation.
• Monitor production agents using observability tools, optimizing performance, latency, and operating costs while protecting customer data and maintaining tenant security.
• Collaborate with engineering leaders and cross-functional teams to understand business challenges and deliver practical solutions that improve customer outcomes and operational efficiency.
• Take ownership of projects from design through deployment and ongoing improvement, proactively identifying opportunities to innovate, simplify processes, and deliver measurable business value.

Kenntnisse

Python development

Java/Spring Boot

AWS serverless

LLM/agent development

Prompt engineering

Performance monitoring

Tools

AWS Bedrock AgentCore

Strands Agents

LangGraph

MCP servers

OpenTelemetry

Jobbeschreibung

Senior Engineer, AI/ML

Location: Denver, CO (Hybrid, 2 days per week in office) or Remote within the United States

Employment Type: Full-Time

Salary Range: $160,000–$190,000

About the Opportunity

We are seeking a Senior Engineer, AI/ML who is excited to build and deploy production-ready AI agents that solve real business problems. This is a hands‑on engineering role for someone who enjoys working in a fast‑paced, growth‑oriented environment, takes ownership of outcomes, and is motivated by turning ideas into practical solutions.

We value engineers who understand that great technology starts with understanding the problem. The right person will know when AI can make a meaningful difference, when a simpler solution is more effective, and how to balance technical innovation with customer impact, cost, and business value.

What You’ll Do

• Design, build, deploy, and maintain production AI agents and multi‑agent workflows using code‑first frameworks and AWS Bedrock AgentCore.
• Develop reusable Python tools, MCP servers, and secure integrations that connect AI agents to APIs, cloud services, and business systems.
• Implement prompt engineering, automated testing, AI evaluation, guardrails, and approval processes to ensure agent accuracy, reliability, and safe operation.
• Monitor production agents using observability tools, optimizing performance, latency, and operating costs while protecting customer data and maintaining tenant security.
• Collaborate with engineering leaders and cross‑functional teams to understand business challenges and deliver practical solutions that improve customer outcomes and operational efficiency.
• Take ownership of projects from design through deployment and ongoing improvement, proactively identifying opportunities to innovate, simplify processes, and deliver measurable business value.

What You’ll Bring

Required Qualifications

• 5+ years of professional software engineering experience, including hands‑on experience building and operating production LLM‑based AI agents using a code‑first framework.
• Strong Python development skills and the ability to read, understand, and contribute to Java/Spring Boot services.
• Hands‑on experience with AWS serverless technologies, such as Lambda, EventBridge, DynamoDB, S3, and Step Functions.
• Experience with prompt engineering, tool or function calling, and evaluating the quality and reliability of LLM outputs.
• Understanding of production software engineering principles, including testing, deployment, monitoring, security, and error handling.
• Demonstrated ability to take ownership of technical projects and deliver working solutions.
• Strong problem‑solving skills and sound business judgment, with the ability to evaluate the value, complexity, and trade‑offs of potential solutions.
• Comfort working in a fast‑paced, evolving environment where priorities may change and engineers are expected to take initiative.

Preferred Qualifications

• Experience with AWS Bedrock AgentCore Runtime, Gateway, Memory, Identity, or related services.
• Experience with Strands Agents, LangGraph, OpenAI Agents SDK, Google ADK, or similar agentic AI frameworks.
• Production experience developing and maintaining MCP servers.
• Experience with automated AI evaluation, LLM‑as‑judge testing, agent governance, or multi‑agent orchestration.
• Experience implementing production observability using OpenTelemetry, CloudWatch, or comparable tools.
• Experience optimizing AI models and workflows for cost, latency, reliability, and performance.
• Familiarity with AWS Bedrock Guardrails and production AI safety practices.
• Experience with AWS services such as API Gateway, Aurora, ECS Fargate, and AWS CDK.
• Familiarity with data pipelines, ETL processes, or data lake technologies such as AWS Glue and Athena.

Industry and Environment Experience

• Experience working in a startup, scale‑up, or high‑growth technology environment where adaptability, initiative, and accountability are important.
• Experience building or supporting SaaS products, cloud‑based platforms, or multi‑tenant applications.
• Automotive industry experience is a plus, particularly experience supporting dealership operations, automotive technology, or related business systems.
• Candidates with strong product engineering experience in other industries are encouraged to apply.
• A track record of working collaboratively, identifying problems, and taking action to improve products or processes.

Technical Environment

AI and Agent Development: AWS Bedrock AgentCore, Strands Agents, LangGraph, MCP servers, Bedrock Guardrails, and Anthropic models.

Cloud Infrastructure: AWS Lambda, EventBridge, DynamoDB, S3, Step Functions, API Gateway, Aurora, ECS Fargate, and AWS CDK.

Programming Languages: Python (primary) and Java/Spring Boot (secondary).

Monitoring and Evaluation: AgentCore session tracing, OpenTelemetry, CloudWatch, automated evaluation pipelines, and LLM‑as‑judge testing.

We use AI as a practical engineering tool and expect team members to incorporate it into their daily workflows. You will use AI‑assisted development tools to accelerate coding, refine prompts and tool schemas, evaluate solutions, and improve development efficiency.

Compensation and Benefits

• Competitive Base Salary
• Health Coverage: Employer‑paid medical, dental, and vision insurance for employees and their families, beginning on day one.
• Flexible Work Options: Hybrid work in Denver, Colorado, with two days per week in the office, or fully remote work from elsewhere in the United States.
• Retirement Benefits: 401(k) plan with company match.
• Paid Time Off: Unlimited PTO and 10 paid holidays.
• Income Protection: Employer‑paid short‑term and long‑term disability coverage.
• Life Insurance: Employer‑paid life and accidental death and dismemberment (AD&D) coverage.
• Mental Health Support: Access to confidential therapy sessions through BetterHelp.
• Additional Benefits: Optional pet insurance and identity theft protection, plus an on‑site gym and stocked kitchen for employees working in the Denver office.

We offer the opportunity to join a growing technology business where your ideas, initiative, and technical contributions can have a meaningful impact. As the company evolves, you will have the opportunity to help shape its products, improve how teams work, and build solutions that support long‑term growth.