Senior AI Engineer

Intellias; Poland; On-site; PLN 240,000 - 360,000; Full time

Job summary

Intellias seeks an AI Engineer to transition AI capabilities from prototype to production, architecting agentic AI systems for planning, reasoning, and executing enterprise workflows.

You will prototype with LangChain, LangGraph, OpenAI/Azure OpenAI, and RAG pipelines, translating concepts into scalable Python services, REST APIs, and modern interfaces.

Qualifications

• Master’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or related field.
• 5+ years of software engineering experience with AI/ML exposure, or equivalent.
• 2+ years of hands-on experience building LLM/Generative AI applications.
• Proven experience designing and building AI Agents / Agentic AI solutions.
• Experience integrating LLM APIs (OpenAI, Azure OpenAI, Anthropic, Gemini).
• Strong experience with LangChain, LangGraph.
• Strong understanding of RAG, embeddings, vector search, retrieval, and re-ranking.
• Experience with Azure AI Search, Pinecone, Weaviate, or pgvector.
• Advanced prompt-engineering knowledge, including ReAct, few-shot, and structured prompting.
• Strong experience with React, TypeScript, Vite, FastAPI, and REST APIs.

Responsibilities

• Architect, design, develop, and deploy single‑agent and multi‑agent AI solutions using modern Microsoft AI technologies.
• Build agentic workflows supporting planning, reasoning, tool execution, loops, interruptions, and human‑in‑the‑loop interventions.
• Use LangChain, LangGraph, or similar state‑based orchestration frameworks.
• Develop secure tool layers enabling agents to interact with internal APIs, databases, and SaaS platforms such as Salesforce, Workday, and ServiceNow.
• Implement agent memory, state persistence, conversational history, context management, and context‑window optimization.
• Evaluate emerging AI models, frameworks, protocols, and tools for enterprise adoption.

Skills

5+ years software engineering

2+ years LLM/Generative AI

AI Agents / Agentic AI

LLM APIs integration

LangChain / LangGraph

RAG, embeddings, vector search

Azure AI Search / Pinecone / Weaviate

Prompt engineering (ReAct, few-shot)

React, TypeScript, Vite, FastAPI, REST

Education

Master’s degree in CS/AI/Data Science/SE or related field

Tools

Azure OpenAI

OpenAI API

Anthropic / Gemini APIs

LangChain / LangGraph

Azure AI Search

Pinecone / Weaviate / pgvector

React / TypeScript / Vite

FastAPI / REST APIs

Job description

Job Overview

We are seeking a highly skilled AI Engineer to help transition AI capabilities from prototype to production. The engineer will architect, develop, deploy, and operate robust Agentic AI systems capable of planning, reasoning, and executing complex enterprise workflows.

The ideal candidate is a hands‑on engineer with strong experience in LLMs, Agentic AI, Python, Azure, RAG, and AI orchestration frameworks. This role requires someone who can rapidly experiment with emerging AI technologies while transforming successful prototypes into scalable, secure, maintainable production applications.

You will collaborate with Product Managers, Business Stakeholders, Data Engineers, Platform Teams, and other technology partners to deliver high‑value enterprise AI solutions.

Project Overview

Our client is a leading multi‑brand technology solutions provider serving business, government, education, and healthcare customers across the U.S., U.K., and Canada. The organization is a Fortune 500 and S&P 500 company, founded in 1984, with approximately 10,000 employees. Its offerings span hardware, software, security, cloud, data centers, networking, and integrated IT solutions.

Key Responsibilities

Agentic AI & Orchestration

• Architect, design, develop, and deploy single‑agent and multi‑agent AI solutions using modern Microsoft AI technologies.
• Build agentic workflows supporting planning, reasoning, tool execution, loops, interruptions, and human‑in‑the‑loop interventions.
• Use LangChain, LangGraph, or similar state‑based orchestration frameworks.
• Develop secure tool layers enabling agents to interact with internal APIs, databases, and SaaS platforms such as Salesforce, Workday, and ServiceNow.
• Implement agent memory, state persistence, conversational history, context management, and context‑window optimization.
• Evaluate emerging AI models, frameworks, protocols, and tools for enterprise adoption.

LLM & Generative AI

• Develop production‑grade AI applications using Python and LLM APIs.
• Integrate models including OpenAI, Azure OpenAI, Anthropic, and Gemini.
• Apply advanced prompt‑engineering techniques such as ReAct, few‑shot, structured prompting, and reasoning‑oriented approaches.
• Rapidly prototype new AI capabilities and convert successful concepts into tested, maintainable production solutions.
• Design for LLM non‑determinism, hallucinations, rate limits, context limitations, latency, and cost.
• Design and implement production‑grade Retrieval‑Augmented Generation (RAG) pipelines.
• Build document ingestion and processing solutions for structured and unstructured data.
• Optimize chunking, embeddings, vector indexing, metadata, retrieval, filtering, and re‑ranking.
• Work with Azure AI Search, Pinecone, Weaviate, or pgvector.
• Partner with Data Engineering teams to create and maintain high‑quality Golden Datasets.
• Improve retrieval precision, grounding, and response quality while reducing hallucinations.

LLMOps, Evaluation & Observability

• Build automated evaluation frameworks for AI applications and agents.
• Implement LLM‑as‑a‑Judge, regression testing, and quality gates within CI/CD.
• Evaluate accuracy, relevance, hallucination, safety, reliability, and agent behavior.
• Implement logging, tracing, monitoring, and observability for AI workflows.
• Monitor agent execution, latency, token consumption, failures, and downstream dependencies.
• Troubleshoot production issues involving rate limits, context overflows, model/API failures, and non‑deterministic behavior.
• Optimize prompts, token usage, caching, model selection, latency, and operating costs.
• Develop scalable backend services using Python, FastAPI, and REST APIs.
• Build modern AI‑enabled interfaces using React, TypeScript, and Vite.
• Develop reusable, secure, maintainable, and well‑tested application components.

Azure, Security & DevOps

• Build and deploy AI applications on Microsoft Azure.
• Work with Azure Storage, Key Vault, Monitor, Application Insights, and Azure AI Search.
• Implement enterprise security using OAuth 2.0, JWT, Microsoft Entra ID, RBAC, and secrets management.
• Develop CI/CD pipelines using GitHub or Azure DevOps, Docker, and YAML.
• Troubleshoot deployments and production issues across development, test, and production environments.
• Ensure solutions are secure, scalable, observable, reliable, and maintainable.
• Stay current with developments in Generative AI, LLMs, Agentic AI, RAG, orchestration, and AI infrastructure.
• Evaluate emerging technologies and recommend solutions for enterprise adoption.
• Collaborate with technical and business stakeholders to deliver AI capabilities aligned with business needs.
• Explain AI limitations and probabilistic behavior clearly to non‑technical stakeholders.
• Document architecture, technical designs, implementation decisions, and operational procedures.
• Share knowledge through documentation, presentations, and mentoring.

Required Qualifications

• Master’s degree in Computer Science, Artificial Intelligence, Data Science, Software Engineering, or related technical field.
• 5+ years of software engineering experience with AI/ML exposure, or equivalent extensive experience.
• 2+ years of hands‑on experience building LLM/Generative AI applications.
• Proven experience designing and building AI Agents / Agentic AI solutions.
• Experience integrating LLM APIs, including OpenAI, Azure OpenAI, Anthropic, Gemini, or similar.
• Strong experience with LangChain, LangGraph, or similar orchestration frameworks.
• Strong understanding of RAG, embeddings, vector search, document chunking, retrieval, and re‑ranking.
• Experience with Azure AI Search, Pinecone, Weaviate, or pgvector.
• Advanced prompt‑engineering knowledge, including ReAct, few‑shot, and structured prompting.
• Strong experience with React, TypeScript, Vite, FastAPI, and REST APIs.