AI Developer

Job summary

Design, develop, and deploy production-grade LLM assistants, agents, and applications using RAG, tool integrations, prompt and context engineering, and enterprise data. Build reusable OpenAI capabilities and secure cloud-native integrations, while supporting evaluation, testing, monitoring, guardrails, and production observability.

Job details

Title – GenAi Developer Location: REMOTE Start Date: ASAP Contract: 1 year to start What we expect of you / Basic Qualifications: Master’s degree with 4+ years of experience in Computer Science, IT, or a related field, OR Bachelor’s degree with 6+ years of experience in Computer Science, IT, or a related field. 4+ years of professional software development and system-design experience. 2+ years of hands-on experience developing and deploying production Generative AI applications, assistants, agents, or RAG solutions using OpenAI preferred, Claude, Gemini, or comparable models. Design, develop, and deploy production-grade LLM-powered assistants, agents, and AI applications on ChatGPT Enterprise and approved AI platforms using RAG, tool integration, prompt/context engineering, and enterprise data. Build and support reusable OpenAI capabilities including Plugins, ChatGPT Skills, Workspace Agents, MCP-based Apps, and, where enabled, Dots and ChatGPT Work; support modernization of legacy Custom GPT workflows. Hands-on experience building agentic and tool-connected AI solutions, including orchestration, tool/function calling, human-in-the-loop patterns, or MCP-based integrations. 2+ years of hands-on cloud-native engineering experience, preferably on AWS using services such as Amazon Bedrock, Lambda, EKS, API Gateway, S3, and related services. 2+ years of hands-on experience with embeddings, vector databases, semantic/hybrid retrieval, and RAG pipelines. Strong programming skills in Python, including development of APIs, integrations, backend services, evaluation utilities, or GenAI applications. Experience with GenAI frameworks and libraries such as OpenAI SDKs, LangChain/LangGraph, Transformers, Hugging Face, or comparable frameworks. Experience designing secure enterprise integrations using REST APIs, API gateways, OAuth/OIDC, service identities, RBAC, secrets management, and enterprise authentication patterns. Experience implementing LLM/RAG evaluation, regression testing, tracing, monitoring, guardrails, and production observability.

What you’ll do

Design, develop, and deploy production-grade LLM assistants, agents, and applications using RAG, tool integrations, prompt and context engineering, and enterprise data. Build reusable OpenAI capabilities and secure cloud-native integrations, while supporting evaluation, testing, monitoring, guardrails, and production observability.

Requirements

Requires a master’s degree with at least 4 years of relevant experience or a bachelor’s degree with at least 6 years, plus 4 or more years of software development and system-design experience. Candidates need hands-on experience with production Generative AI, Python, cloud-native engineering, RAG and vector retrieval, agentic integrations, enterprise security, and LLM evaluation and observability.

Listed skills

• Python · Preferred
• Amazon Web Services · Preferred
• REST APIs · Preferred

Other relevant skills

Identified from the job description. Confirm important requirements above.

• Python
• Generative AI
• Large Language Models
• Retrieval-Augmented Generation
• OpenAI
• Agentic AI
• Cloud-Native Engineering
• AWS
• Amazon Bedrock
• Vector Databases
• Embeddings
• LangChain
• LangGraph
• REST APIs
• OAuth/OIDC
• LLM Evaluation

Job areas

• Technology
• Software
• Data & Analytics
• Engineering

More jobs from Experis Canada