AI Systems Engineer

Overview:

About Suffolk

Suffolk is a national enterprise that builds, innovates, and invests. We provide value across the entire project lifecycle through our core construction management services and complementary business lines in real estate investment, design, self-perform construction, and technology start-up investment (Suffolk Technologies). By integrating data, artificial intelligence, and advanced technology through our Seamless Platform, we connect design, construction, and operations to deliver smarter, more predictable results and redefine how America builds.

Suffolk – America’s Contractor – is a national company with more than $9 billion in annual revenue, 3,000 employees, and 17 offices, including Boston (headquarters), New York City, Miami, West Palm Beach, Tampa, Estero, Dallas, Los Angeles, San Francisco, San Diego, Las Vegas, Herndon, U.S. Virgin Islands, and other key markets. Suffolk manages some of the most complex and transformative projects in the country, serving clients across healthcare, life sciences, education, gaming, aviation, transportation, government, mission critical, and commercial sectors. Suffolk is privately held and is led by founder, chairman and CEO John Fish. Suffolk is ranked #8 on ENR’s list of “Top CM-at-Risk Contractors.” For more information, visit www.suffolk.com and follow Suffolk on Facebook, Twitter, LinkedIn, YouTube, and Instagram.

At Suffolk, we believe that our total rewards program should offer you and your family the support you need when it matters most. That’s why we have created a program that provides employees with access to a wide variety of options that can be personalized to support you and your loved ones physically, emotionally, and financially.

Benefits include, competitive salaries, auto allowances and gas cards for certain roles, access to market leading medical and emotional and mental health benefits, dental, and vision insurance plans, virtual care options for physical therapy and primary care, generous paid time off, 401k plan with employer match and access to expert financial resources, company paid and voluntary life insurance, tax deferred savings accounts, 10 backup daycare days each year, short- and long-term disability, commuter benefits and more. For more information, click here.

Role Summary

Join Suffolk’s AI Studio in Boston as an AI Systems Engineer, a hybrid role responsible for architecting and building both:

The distributed systems backbone that powers enterprise-scale AI, and

The agentic and LLM-driven capabilities transforming construction workflows

This role sits at the intersection of platform engineering and applied AI. You will design scalable APIs, event-driven services, and reliable infrastructure - while also implementing multi-model AI agents, retrieval pipelines, and AI orchestration frameworks that operate in real-world production environments.

You will help define how AI is built, deployed, observed, and scaled across Suffolk’s national operations.

Responsibilities:

AI & Agentic Systems Product Engineering & Deployment

Design and implement production-grade RAG architectures

Build and deploy multi-model AI agents leveraging AWS Bedrock and LLM providers (Claude, GPT, Llama, Titan, etc.)

Implement dynamic model routing strategies based on task complexity, cost, and latency

Develop multi-agent orchestration frameworks enabling collaborative workflows (planner, retriever, executor, summarizer)

Design safe tool invocation patterns and guardrails for enterprise AI agents

Optimize inference pipelines for cost, performance, and reliability

Implement evaluation frameworks to measure model performance, hallucination rates, and response quality

Design fallback and degradation strategies for model outages or latency spikes

Distributed Systems & Platform Architecture

Architect and evolve service-oriented and event-driven systems supporting AI workloads

Design REST/GraphQL APIs with clear versioning, authentication, and backward compatibility strategies

Implement asynchronous processing pipelines using queues, event buses, and workflow orchestration

Ensure reliability through idempotent consumers, retry strategies, circuit breakers, and dead-letter queues

Make informed tradeoffs between relational, NoSQL, and vector storage systems

Build services that are observable, traceable, and production-ready

Define and document architectural standards for AI platform services

Implement LLMOps: cost monitoring, latency optimization, usage analytics, and model versioning

Enforce security, governance, and access standards in line with enterprise policies

Collaboration & Technical Leadership

Work closely with product managers, site AI engineers, and data scientists to iterate rapidly in Agile sprints

Communicate technical progress clearly to non-technical stakeholders; contribute to internal AI playbooks and templates

Qualifications:

6+ years of professional software engineering experience (not including vibe coding)

Demonstrated experience designing distributed or service-oriented systems in production

Strong backend engineering skills in Python, and at least one of Java, NodeJS, Rust or Kotlin

Experience building and deploying event-driven architectures (SNS/SQS, Kafka, EventBridge, etc.)

Experience integrating LLMs into production systems (Bedrock, OpenAI, Anthropic, etc.).

Hands-on experience with RAG pipelines, vector databases and building multi-agent AI systems

Deep understanding of:

Distributed system failure modes

API lifecycle management

Concurrency and consistency tradeoffs

LLM cost, latency, and reliability constraints

Tuning AI Agents for accuracy and performance

Preferred

Experience building internal AI platforms or shared infrastructure

Exposure to large-scale SaaS or mission-critical systems

Experience designing multi-agent or orchestration frameworks

Experience with Databricks Lakehouse architecture

Prior experience in construction, manufacturing, or operational industries

What Makes This Role Unique

This role requires equal fluency in:

Designing distributed systems that scale

Engineering intelligent agentic systems that reason

We are looking for engineers who understand that production AI is not just about model quality and prompt engineering - it is also about the systems that deliver, monitor, and evolve those models and agents safely at scale.

Working Conditions:

While performing the duties of this job, the employee is regularly required to sit for long periods of time; talk or hear; perform fine motor, hand and finger skills in the use of a keyboard, telephone, or writing. The employee is frequently required to stands; walk; and reach with arms and/or hands. Specific vision abilities include close vision, distance vision, depth perception and the ability to adjust focus. The employee will spend their time in an office environment with a quiet to moderate noise level. Job site walking.

Suffolk provides equal employment opportunities to all employees and applicants for employment without regard to race, color, religion, sex, sexual orientation, pregnancy or maternity, national origin, citizenship, genetic information, disability, protected veteran, gender identity, age or any other status protected by law. This policy applies to recruiting, hiring, transfers, promotions, terminations, compensation, benefits, and all other terms and conditions of employment. Suffolk will not tolerate any unlawful discrimination toward, or harassment of, applicants or employees by anyone at Suffolk, or anyone working on behalf of Suffolk.

Compensation Information:

The expected salary range for this position (AI Engineer) in US-MA-Boston is between $152,000 and $222,600 USD. This represents the typical salary range for this position and is just one component of Suffolk’s total compensation package. Actual salaries may be based on several factors including, but not limited to, skill set, experience, education and other qualifications. Suffolk offers a comprehensive benefits package as part of its overall compensation strategy. Salary ranges may differ by geography and are reviewed regularly to reflect market trends.