Software Engineer - Agentic AI

Hyrr Ai — Canada · Posted ~20 hours ago

Mid Full-time

Skills

Python LLMs agentic AI context engineering LLM orchestration RAG APIs evaluation frameworks

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

Join an AI engineering team focused on building sophisticated agentic systems. You will design autonomous workflows powered by large language models, optimize context and retrieval, connect models to external tools and services, and develop evaluation systems that improve reliability, safety, and predictable behavior in production.

Highlights

Build sophisticated autonomous AI systems using LLMs, with hands-on work across agentic workflows, context engineering, RAG, tool integration, evaluation, and production safety.

Description

We are seeking a talented and driven Software Engineer to join our AI initiatives team, focusing heavily on developing sophisticated agentic solutions. In this role, you will be responsible for designing and implementing autonomous systems that leverage Large Language Models (LLMs) to reason, plan, and execute complex workflows. A deep understanding of context engineering, tool usage, and LLM orchestration is essential. Key Responsibilities Design, build, and deploy agentic workflows that can autonomously solve multi-step problems using tools and APIs.Perform advanced context engineering to optimize LLM prompts, manage context windows efficiently, and implement Retrieval-Augmented Generation (RAG) pipelines.Integrate LLMs with external systems, databases, and third-party APIs to enable agentic actions.Develop evaluation frameworks to monitor agent performance, reduce hallucinations, and ensure safe and predictable behavior in production environments.Collaborate with product and data teams to identify opportunities for AI-driven automation and intelligent feature development. Qualifications Proficiency in Python and experience with backend framework development.Hands-on experience with LLM orchestration frameworks (e.g., LangChain, LlamaIndex, AutoGen).Strong background in context engineering, prompt optimization, and working with top-tier LLM APIs (Gemini, OpenAI, Anthropic).Experience building and scaling RAG architectures using vector databases (e.g., Pinecone, Weaviate, Milvus).Solid understanding of system design principles, especially for distributed and asynchronous systems.