← Back to jobsJob ID col-cmvv4358903jj42b9vyx1nyqj

Public companyPosted 30+ days ago

Staff Software Engineer – AI

Full-time
Hybrid
7+ years
$147K – $273K/yr
Posted 30+ days ago

Thomson Reuters is hiring a Staff Software Engineer – AI for its Confirmation Product Engineering team. The role builds and delivers production backend, platform, and AI/ML capabilities, while providing hands-on technical leadership for scalable AI and distributed systems.

Posted
30+ Days Ago
Source
thomsonreuters.wd5.myworkdayjobs.com
Sector
Information Technology & AI

Opens the employer's application page in a new tab

Responsibilities

  • Architect, develop, and deliver production backend and platform services using C#/.NET, PostgreSQL, AWS, microservices, and distributed-system patterns
  • Build production AI/ML capabilities using Python, including LLM integration, AI agents, orchestration, retrieval, and multi-step AI workflows
  • Lead hands-on AI engineering initiatives across product and infrastructure, including agent-based workflows, retrieval systems, and AI-assisted document processing
  • Build and evolve AI orchestration capabilities, including routing, tool calling, MCP servers, multi-step workflows, safety controls, guardrails, evaluation, and resilient error handling around third-party LLMs
  • Design reliable, scalable, high-throughput distributed systems and AI workloads, incorporating caching, queuing, rate limiting, model failover, observability, resilience, and cost/performance optimization
  • Develop retrieval and data capabilities using document search, vector stores, embeddings, semantic search, and indexing strategies for large-scale audit and confirmation use cases
  • Provide hands-on Staff-level technical leadership by setting technical direction, influencing engineering standards, mentoring engineers, and continuing to personally design, code, build, and deliver production systems

Qualifications

  • Bachelor's degree in Computer Science, Computer Engineering, a related field, or equivalent professional experience
  • 7+ years of progressive software engineering experience, including hands-on development, architecture, and delivery of large-scale production systems
  • Strong, recent, hands-on C#/.NET production development experience, including building backend services and APIs using C#/.NET and ASP.NET Core or similar technologies
  • Hands-on Python experience for AI/ML system development, including model integration, AI orchestration, APIs, data pipelines, or comparable production use cases
  • Demonstrated experience personally building and delivering AI/ML features into production, including LLM-powered applications, AI agents, retrieval/RAG, orchestration, or comparable AI-native capabilities
  • Strong hands-on platform and distributed-systems engineering experience, including microservices, system integration, data modeling, REST or GraphQL APIs, relational databases, observability, resilience, scalability, and performance optimization
  • Experience implementing appropriate AI safety controls, guardrails, evaluation, reliability, and production operational practices
  • Proven experience leading complex engineering initiatives from architecture and hands-on implementation through deployment, rollout, and long-term production operation
  • Proven ability to operate as a hands-on Staff-level technical leader, providing technical direction and mentoring engineers while continuing to actively design, code, build, and deliver production software
  • Strong communication and cross-functional collaboration skills with the ability to partner effectively with engineering, product, design, user experience, research, and machine learning teams
  • Candidates must have hands-on production AI delivery experience
  • AI experience limited to personal projects, side projects, coursework, experimentation, or proof-of-concept work alone does not meet this requirement

Preferred

  • Hands-on experience integrating LLM APIs such as OpenAI or Anthropic into production applications, including prompt and response management, cost controls, reliability, and safety considerations
  • Experience with vector databases, embeddings, semantic search, and custom retrieval pipelines
  • Experience designing automated testing, AI evaluation, reliability, and release practices for systems with non-deterministic model behavior
  • Familiarity with actor-model architectures and frameworks, such as Microsoft Orleans or Akka, for resilient, message-driven distributed systems
  • Experience with AWS, containerized microservices using Docker and Kubernetes, and CI/CD pipelines such as GitHub Actions or similar technologies
  • Experience with modern JavaScript frameworks, particularly Angular and TypeScript
  • Experience working in industries where correctness, auditability, security, and regulatory compliance are important, such as financial technology, audit, tax, or legal technology
  • Experience interacting directly with customers and translating customer or business needs into scalable technical solutions

Required skills

AI Agents and OrchestrationASP.NET CoreAWSC#/.NETDistributed SystemsDocker and KubernetesEmbeddingsLLM IntegrationProduction AI/ML EngineeringPythonRelational DatabasesRetrieval-Augmented Generation (RAG)Semantic SearchVector Databases

Full job description

Thomson Reuters is hiring a Staff Software Engineer – AI for its Confirmation Product Engineering team. The role builds and delivers production backend, platform, and AI/ML capabilities, while providing hands-on technical leadership for scalable AI and distributed systems.

Responsibilities

  • Architect, develop, and deliver production backend and platform services using C#/.NET, PostgreSQL, AWS, microservices, and distributed-system patterns
  • Build production AI/ML capabilities using Python, including LLM integration, AI agents, orchestration, retrieval, and multi-step AI workflows
  • Lead hands-on AI engineering initiatives across product and infrastructure, including agent-based workflows, retrieval systems, and AI-assisted document processing
  • Build and evolve AI orchestration capabilities, including routing, tool calling, MCP servers, multi-step workflows, safety controls, guardrails, evaluation, and resilient error handling around third-party LLMs
  • Design reliable, scalable, high-throughput distributed systems and AI workloads, incorporating caching, queuing, rate limiting, model failover, observability, resilience, and cost/performance optimization
  • Develop retrieval and data capabilities using document search, vector stores, embeddings, semantic search, and indexing strategies for large-scale audit and confirmation use cases
  • Provide hands-on Staff-level technical leadership by setting technical direction, influencing engineering standards, mentoring engineers, and continuing to personally design, code, build, and deliver production systems

Preferred

  • Hands-on experience integrating LLM APIs such as OpenAI or Anthropic into production applications, including prompt and response management, cost controls, reliability, and safety considerations
  • Experience with vector databases, embeddings, semantic search, and custom retrieval pipelines
  • Experience designing automated testing, AI evaluation, reliability, and release practices for systems with non-deterministic model behavior
  • Familiarity with actor-model architectures and frameworks, such as Microsoft Orleans or Akka, for resilient, message-driven distributed systems
  • Experience with AWS, containerized microservices using Docker and Kubernetes, and CI/CD pipelines such as GitHub Actions or similar technologies
  • Experience with modern JavaScript frameworks, particularly Angular and TypeScript
  • Experience working in industries where correctness, auditability, security, and regulatory compliance are important, such as financial technology, audit, tax, or legal technology
  • Experience interacting directly with customers and translating customer or business needs into scalable technical solutions
  • LLM API Integration
  • Prompt Management
  • Response Management
  • Cost Controls
  • AI Safety
  • Vector Databases
  • Embeddings
  • Semantic Search
  • Retrieval Pipelines
  • Automated Testing
  • System Reliability
  • Release Practices
  • Actor-Model Architectures
  • Microsoft Orleans
  • Akka
  • AWS
  • Docker
  • Kubernetes
  • CI/CD
  • GitHub Actions
  • JavaScript
  • Angular
  • TypeScript
  • Financial Technology
  • Audit
  • Tax Technology
  • Legal Technology
  • Auditability
  • Security
  • Regulatory Compliance
  • Scalable Solution Design
  • Customer Interaction
  • Requirements Translation

Benefits

  • Hybrid work model for office-based roles
  • Flexible work arrangements, including work from anywhere for up to 8 weeks per year
  • Flexible vacation
  • Two company-wide Mental Health Days off
  • Access to the Headspace app
  • Retirement savings
  • Tuition reimbursement
  • Employee incentive programs
  • Resources for mental, physical, and financial wellbeing
  • Two paid volunteer days off annually
  • Opportunities to get involved with pro-bono consulting projects and Environmental, Social, and Governance (ESG) initiatives
  • For employees in the United States: health, dental, vision, disability, and life insurance programs
  • For employees in the United States: 401k plan with company match
  • For employees in the United States: competitive vacation, sick and safe paid time off, and paid holidays, including two company mental health days off
  • For employees in the United States: parental leave
  • For employees in the United States: sabbatical leave
  • For employees in the United States: optional hospital, accident and sickness insurance paid 100% by the employee
  • For employees in the United States: optional life and AD&D insurance paid 100% by the employee
  • For employees in the United States: Flexible Spending and Health Savings Accounts
  • For employees in the United States: fitness reimbursement
  • For employees in the United States: access to Employee Assistance Program
  • For employees in the United States: Group Legal Identity Theft Protection benefit paid 100% by the employee
  • For employees in the United States: access to 529 Plan
  • For employees in the United States: commuter benefits
  • For employees in the United States: Adoption & Surrogacy Assistance
  • For employees in the United States: access to Employee Stock Purchase Plan
  • Annual bonus based on a combination of enterprise and individual performance, if eligible

Company

  • Professional software and information services for legal, tax, and compliance.
  • Toronto, Ontario, CAN
  • http://thomsonreuters.com/
  • Founded in 1851
  • 10001+ employees

Qualifications

  • Bachelor's degree in Computer Science, Computer Engineering, a related field, or equivalent professional experience
  • 7+ years of progressive software engineering experience, including hands-on development, architecture, and delivery of large-scale production systems
  • Strong, recent, hands-on C#/.NET production development experience, including building backend services and APIs using C#/.NET and ASP.NET Core or similar technologies
  • Hands-on Python experience for AI/ML system development, including model integration, AI orchestration, APIs, data pipelines, or comparable production use cases
  • Demonstrated experience personally building and delivering AI/ML features into production, including LLM-powered applications, AI agents, retrieval/RAG, orchestration, or comparable AI-native capabilities
  • Strong hands-on platform and distributed-systems engineering experience, including microservices, system integration, data modeling, REST or GraphQL APIs, relational databases, observability, resilience, scalability, and performance optimization
  • Experience implementing appropriate AI safety controls, guardrails, evaluation, reliability, and production operational practices
  • Proven experience leading complex engineering initiatives from architecture and hands-on implementation through deployment, rollout, and long-term production operation
  • Proven ability to operate as a hands-on Staff-level technical leader, providing technical direction and mentoring engineers while continuing to actively design, code, build, and deliver production software
  • Strong communication and cross-functional collaboration skills with the ability to partner effectively with engineering, product, design, user experience, research, and machine learning teams
  • Candidates must have hands-on production AI delivery experience
  • AI experience limited to personal projects, side projects, coursework, experimentation, or proof-of-concept work alone does not meet this requirement
  • Hands-on experience integrating LLM APIs such as OpenAI or Anthropic into production applications, including prompt and response management, cost controls, reliability, and safety considerations
  • Experience with vector databases, embeddings, semantic search, and custom retrieval pipelines
  • Experience designing automated testing, AI evaluation, reliability, and release practices for systems with non-deterministic model behavior
  • Familiarity with actor-model architectures and frameworks, such as Microsoft Orleans or Akka, for resilient, message-driven distributed systems
  • Experience with AWS, containerized microservices using Docker and Kubernetes, and CI/CD pipelines such as GitHub Actions or similar technologies
  • Experience with modern JavaScript frameworks, particularly Angular and TypeScript
  • Experience working in industries where correctness, auditability, security, and regulatory compliance are important, such as financial technology, audit, tax, or legal technology
  • Experience interacting directly with customers and translating customer or business needs into scalable technical solutions
  • 7+ years of progressive software engineering experience, including hands-on development, architecture, and delivery of large-scale production systems.

Required skills

  • AI Agents and Orchestration, ASP.NET Core, AWS, C#/.NET, Distributed Systems, Docker and Kubernetes, Embeddings, LLM Integration, Production AI/ML Engineering, Python, Relational Databases, Retrieval-Augmented Generation (RAG), Semantic Search, Vector Databases

Experience

  • 7+ years

Job details

Employment type

Full-time

Seniority level

7+ years

Date posted

Oct 2, 2026

Work mode

Hybrid

Job source

thomsonreuters.wd5.myworkdayjobs.com

Company

Public company

Information Technology & AI

Professional software and information services for legal, tax, and compliance.

See all 835 jobs from Public company →

Similar jobs

Matched on role, skills and location · live jobs only

See more AI Engineer jobs in Brooklyn

Capco

1d ago

New

Sr. AI Engineer

Full-timeHybridOrlando, FLCompetitive

Capco is hiring a Senior GenAI Engineer for its Technology Delivery Team. The role develops and deploys scalable generative AI solutions for financial services clients, contributing across the AI lifecycle from experimentation and prototyping to production.

Why similarSame roleAWSEmbeddings

CCC Intelligent Solutions

1d ago

New

Senior AI Engineer

Full-timeRemoteUnited States$180K – $225K/yr

CCC Intelligent Solutions develops technology for the insurance, claims, and repair industries. The Senior AI Engineer owns LLM-powered systems and agentic workflows end to end, including delivery, evaluation, security, and production operation.

Why similarSame roleAWSRemote

Yotta Systems Inc

1d ago

New

Generative AI Engineer

Full-timeRemoteUnited StatesCompetitive

Yotta Systems Inc is seeking a Generative AI Engineer to develop AI applications using Python, LLMs, and retrieval-augmented generation. The role involves building AI agents and integrating REST APIs.

Why similarSame roleAWSRemote

Get new AI Engineer jobs in Brooklyn by email

Create job alert

Staff Software Engineer – AI

Public company · $147K – $273K/yr

Apply on company site