Senior AI Engineer role at Keyrus focused on delivering AI solutions and leading a team. Engage with clients to translate business needs into AI strategies and solutions.
Responsibilities
Translate business objectives into AI solutions — work directly with clients and stakeholders (executives, managers, and technical teams) to understand challenges, quantify value, and define success metrics before building.
Lead platform and tooling decisions : evaluate and recommend the right approach for each use case, staying true to our vendor-agnostic DNA: AWS, Azure, Salesforce, a custom orchestration stack, and others, based on data gravity, integration, cost, governance, and time-to-value.
Deliver clear trade-off analyses that executives and engineers both understand.
Architect agentic & generative AI systems : design multi-agent workflows, RAG pipelines, tool/function calling, memory and state management, guardrails, and human-in-the-loop fallbacks.
Build, hands-on : develop production-grade agents and automations with LangChain, LangGraph, Bedrock AgentCore, and other tools to integrate with enterprise systems (CRM, ERP) via APIs.
Own quality and reliability : implement evaluation pipelines, observability, prompt/version management; optimize latency, cost, and accuracy of inference.
Deliver PoCs, demos, and production solutions : move ideas from prototype to scaled deployment with proper CI/CD and AI and MLOps practices.
Contribute to pre-sales and solutioning : shape solution offerings, support proposals, and bring market knowledge and technical credibility to client conversations.
Lead and mentor : provide guidance to engineers and interns, define best practices, and help build and scale our AI practice.
Stay ahead : keep pace with a fast-moving field (new models, frameworks, MCP, agent protocols) and bring well-judged ideas to clients and teams.
Requirements
Degree in Computer Science, Engineering, Data Science, or related field, or equivalent professional experience.
5+ years in software/AI/data engineering, including hands-on experience shipping generative or agentic AI to production
Strong Python and solid software-engineering fundamentals (APIs, microservices, version control, testing).
Hands-on experience building AI agents / tool-using LLMs with an orchestration framework.
Practical experience with AWS AI services , especially Amazon Bedrock (foundation models, agents, guardrails) and the broader AWS stack (Lambda, API Gateway, S3, IAM).
Senior AI Software Engineer building agentic AI harnesses for Kinaxis’s Databricks - based enterprise data fabric. Enabling secure, governed workflows across GCP and Azure.
Technical lead building safe, evaluable LLM agents and AI infrastructure for OpenLoop’s telehealth platform. Setting architecture, observability, retrieval, and model operations direction.
Senior software engineer evaluating AI coding agents such as Codex and Claude Code. Providing rigorous written and video feedback on engineering quality.
Senior software engineer evaluating AI coding agents for G2i. Assessing engineering judgment, explanations, and trustworthiness across Codex, Claude Code, and Cursor.
Senior engineer evaluating AI coding agents such as Codex, Claude Code, and Cursor. Providing rigorous written and video feedback on engineering judgment, reasoning, and interaction quality.
Forward Deployed Engineer building full - stack AI solutions on AWS and Azure for Huron’s consulting clients. Partnering daily with business users to deliver tested features.
Staff AI Security Engineer securing EQ Bank’s enterprise AI, machine learning, and cloud platforms. Building guardrails, controls, automation, and detection capabilities for Canada’s Challenger Bank.
Staff Software Engineer owning OAuth, authorization, and agent delegation systems. Building governed identity infrastructure for Redpanda’s enterprise AI data platform.
Senior software engineer evaluating AI coding agents for G2i’s engineering team. Assessing reasoning, explanations, and engineering judgment in Codex, Claude Code, and Cursor interactions.
Senior software engineer evaluating AI coding agents such as Codex, Claude Code, and Cursor. Providing rigorous written and video feedback on engineering quality.