Role Overview

The AI Engineer is the hands-on builder across IE pods — responsible for creating the agentic workflows, retrieval systems, data pipelines, evaluation harnesses, and product integrations that bring IE’s frontier capabilities to life. You operate at the intersection of LLMs, vector search, data engineering, and modern application development, turning architecture and functional intent into robust, reliable, real-world intelligence.

Across multiple pods and functional domains, you will design and implement systems that integrate models, multimodal data, APIs, and enterprise services. You build the connective tissue that allows agents to reason, retrieve, evaluate, and act. Whether the pod focuses on Finance, Operations, Supply Chain, Engineering, or Investments, you ensure the underlying intelligence behaves predictably, efficiently, and safely.

This role demands strong engineering discipline, a deep understanding of emerging AI patterns (RAG, agents, validators, evaluators), and the ability to ship clean, high-quality increments every sprint — even as the frontier moves. You embrace ambiguity, break down complex problems, and collaborate closely with architects, tech leads, UX designers, QA, and functional leads.

You are the person who builds the thing — the systems, the behaviors, the intelligence — that defines the next generation of the IE.

Responsibilities

1. Build AI Features & Agentic Workflows

· Implement multi-agent orchestration, retrieval pipelines, validator agents, and agent actions.

· Develop prompt templates, structured tools, and reasoning workflows aligned to pod requirements.

2. Retrieval, Vector Search & Data Pipelines

· Build and optimize vector search pipelines (FAISS, Milvus, Elasticsearch/OpenSearch, Pinecone, etc.).

· Implement retrieval strategies, embeddings, chunkers, ranking, and data-prep flows.

· Construct ETL/ELT pipelines supporting model and agent runtime.

3. Model Integration, Fine-Tuning & Evals

· Integrate LLMs (Azure OpenAI, Bedrock, Anthropic, etc.) into application workflows.

· Support lightweight fine-tuning, adapter models, or domain adaptation processes.

· Create evaluation suites (unit evals, behavioral tests, A/B experiments) for reliability and drift detection.

4. API, Backend & Product Integrations

· Develop and maintain API endpoints powering agent actions or retrieval layers.

· Integrate with application surfaces (web apps, dashboards, status surfaces, messaging interfaces).

· Work closely with UX/FE teams to ensure clean handoffs and stable data contracts.

5. Observability, Logging & Instrumentation

· Build instrumentation for latency, cost, error modes, and behavioral failures.

· Partner with AI Ops to support deployments, monitoring, and rollback.

· Ensure proper logging for audit trails, compliance, and troubleshooting.

6. Engineering Practices & SDLC Discipline

· Write clean, documented Python code with tests, linters, and version control discipline.

· Participate in code reviews, design reviews, and backlog refinement.

· Follow IE’s 12-week pod structure with predictable output each sprint.

Required Skills & Experience

Technical Skills

· Strong Python engineering experience (3–6+ years).

· Experience with vector databases, embeddings, and retrieval systems.

· Hands-on experience building RAG, agentic workflows, or similar AI patterns.

· Familiarity with model evaluation, testing, and observability tools.

· Solid knowledge of APIs, microservices, and data-centric integrations.

· Comfort with cloud platforms (Azure, AWS, GCP) and CI/CD workflows.

Foundational Engineering Skills

· Excellent debugging, profiling, and performance optimization skills.

· Strong understanding of source control (Git), branching, PR reviews.

· Ability to work in structured agile environments with clear sprint increments.

Mindset

· High ownership, curiosity, and willingness to experiment.

· Loves hard problems and iterating on prototypes.

· Comfortable working in fast-changing frontier environments.

· Values clarity, structure, and quality in code.

Success Criteria (12-Week Pod)

· AI features delivered on-time, with clean code and strong reliability.

· Retrieval and agentic workflows behave consistently under load.

· Evaluations and instrumentation provide clear insight into agent performance.

· Integrations are stable, documented, and testable.

· Pod velocity improves as engineers ramp and systems stabilize.

‍

‍

Start date: ASAP

HackerRank Challenge: Yes

Remote vs Onsite: Fully remote, with possible occasional in person team sessions / workshops / gatherings (i.e. 1x quarter) likely to take place in Prague

US Hours overlap needed: Minimum 2-6pm CET, preferred 2-7pm CET

‍