Deloitte

Audits companies and advises on tax and technology

GenAI Engineer

AI Application EngineeringConfirmed live in the last 24 hours

Full-timePrague, Czechia

About the Job

Requirements

Have at least 2 years of experience as an AI Engineer or equivalent, with a strong focus on generative AI implementation; a natural language processing background for retrieval-augmented generation and Talk2Document work is desirable.
Build production application programming interfaces or services using Python, FastAPI, or a similar framework.
Have built agentic systems using LangGraph, LangChain, PydanticAI, CrewAI, or similar frameworks.
Integrate tools and data safely, including handling timeouts, retries, idempotency, and rate limiting.
Have experience with retrieval-augmented generation and vector search, using Azure AI Search, Pinecone, Redis Vector, Milvus, or Chroma.
Have shipped Talk2Data or Talk2Document-style solutions, or similar patterns.
Use evaluation harnesses and regression suites, and debug with LangSmith, Langfuse, or Datadog.
Be familiar with Model Context Protocol and secure model-to-tool or data connectivity.
Have an EU work permit.
Have cloud experience; Azure is preferred, and AWS or Google Cloud Platform experience is acceptable.

Responsibilities

Build agent workflows using LangGraph, LangChain, PydanticAI, or CrewAI, including routing, retries, fallbacks, timeouts, and human-in-the-loop processes.
Build robust tool-calling integrations with APIs, databases, and internal services, using clean contracts, predictable behavior, and safe error handling such as retries, timeouts, idempotency, and rate limiting.
Build hybrid systems combining pre-built agents with a custom orchestration layer, including interfaces, policies, guardrails, and reuse.
Implement Model Context Protocol servers and clients so models can safely access tools and data, including databases, APIs, and files, using least-privilege patterns and audit-friendly logging.
Build retrieval-augmented generation and knowledge systems, including chunking, embeddings, indexing, retrieval strategies, grounding patterns, vector search, and document ingestion with Azure Document Intelligence.
Develop Talk2Data solutions for safe querying and interpretation of enterprise data.
Develop Talk2Document solutions for question answering, summarization, extraction, and reasoning over documents with citations and grounding.
Implement evaluation and observability, including automated evaluation of task success, groundedness, relevance, safety, latency, and cost; regression suites; and run tracing for debugging with LangSmith, Langfuse, or Datadog.
Build cloud generative AI solutions using Azure OpenAI, Azure AI Foundry, Azure AI Search, Azure Document Intelligence, and Azure Content Safety, or equivalent AWS or Google Cloud Platform services and search or document pipelines.

Desired Qualifications

Experience with agent-to-agent patterns or coordination.
Experience with agent-builder frameworks such as Azure AI Foundry, AWS Bedrock Agents, or Vertex AI Agent Builder.

Who we are looking for

🎯We’re building agentic systems that do real work in production: tool-using workflows, RAG, structured outputs, guardrails, and measurable quality. If you like shipping and iterating fast - but still care about doing it properly - this is the team.

You’ll work with Solution Architects and LLMOps, but your focus is simple: build the thing, make it reliable, and keep improving it.

🔎What you bring:

2+ years as a AI Engineer (or equivalent) with a strong focus on Gen AI implementation; ideally some NLP background for RAG and Talk2Document work.
Python-first engineer who can build production APIs/services (FastAPI or similar).
You’ve built agentic systems with LangGraph / LangChain / PydanticAI / CrewAI (or similar).
You’re comfortable integrating tools/data safely (timeouts, retries, idempotency, rate limiting).
You’ve worked with RAG/vector search (Azure AI Search, Pinecone, Redis Vector, Milvus/Chroma).
You’ve shipped Talk2Data and/or Talk2Document-style solutions (or very similar patterns).
You care about quality: eval harnesses + regression suites, and you can use LangSmith/Langfuse/Datadog to debug what’s happening.
Familiar with MCP and secure model-to-tool/data connectivity.
Bonus: A2A patterns / agent-to-agent coordination.
Bonus: agent builder frameworks (Azure AI Foundry, AWS Bedrock Agents, Vertex AI Agent Builder, or similar).
Cloud experience: Azure preferred, AWS/GCP fine.
EU work permit is required

Your future role

🚀What you will build:

Agent workflows with LangGraph / LangChain / PydanticAI / CrewAI (routing, retries, fallbacks, timeouts, human-in-the-loop).
Tool calling that doesn’t break: APIs, databases, and internal services with clean contracts, predictable behavior, and safe error handling (retries/timeouts, idempotency, rate limiting).
Hybrid systems: pre-built agents plus a thin custom orchestration layer (interfaces, policies, guardrails, reuse).
MCP integrations: implement MCP servers/clients so models can safely access tools/data (DBs/APIs/files) using least-privilege patterns and audit-friendly logging.
RAG + knowledge systems: chunking, embeddings, indexing, retrieval strategies, grounding patterns; vector stacks like Azure AI Search, Pinecone, Redis Vector, Milvus/Chroma; doc ingestion with Azure Document Intelligence.

Real use cases:

Talk2Data (safe querying + interpretation of enterprise data)
Talk2Document (Q&A/summarize/extract/reason over docs with citations/grounding)
Evaluation + observability: automated evals (task success, groundedness/relevance, safety, latency, cost), regression suites, and run tracing for debugging using LangSmith / Langfuse / Datadog.
Cloud GenAI: Azure OpenAI / Azure AI Foundry + Azure AI Search / Document Intelligence / Content Safety. AWS/GCP equivalents welcome (Bedrock/Vertex AI + search/document pipelines).

What we offer

A global network + a strong regional AI&D community (~160 people).
A dedicated technical team that’s actively growing and open to experimenting with new tech (when it actually helps).
Consultancy work, but on real problems with real impact - solutions people use
Specialization in GenAI and adjacent areas, with strong support for continuous learning and obtaining internationally recognized certificates.
Hybrid way of work in a modern Prague office.
International environment where personal development and growth are supported and highly encouraged.
Unique opportunity for a long‑term career and promotions within Deloitte.
Attractive and competitive salary, including a wide range of fringe benefits:
Annual performance bonus rewarding excellence and dedication.
Flexible benefits package via cafeteria system (meals, pension, sports, culture, and more).
Extra time off, including additional vacation and sick days.
Health, travel and life insurance to support your wellbeing and peace of mind.
Support during important life events, such as illness or parental leave.
Professional development through internal and external trainings, cloud partner certifications and mentoring.
Access to sports, wellbeing and social activities, plus a friendly, inclusive team culture.

Also:

✨ Professional Growth –Continuous learning with access to trainings (Azure, GCP, AWS, Databricks), free certifications vouchers and business udemy.com subscription, and mentorship

💰 Attractive Package – Competitive salary, performance bonuses, meal vouchers, extra vacation days, and flexible benefits.

🌍 International Projects – Work with leading companies across Europe and beyond.

📈Career Development – Clear paths for advancement into senior consultant and manager roles.

🏢 Modern Workplace in Prague – Hybrid working model with a centrally located office.

🎉 Culture & Community – Friendly, diverse teams, team-building events, and supportive leadership.

#LI-AN2

About the Company

Deloitte

Audits companies and advises on tax and technology

Deloitte audits companies and advises businesses and governments on tax, technology, and risk, and it is one of the Big Four, the world's four largest accounting firms. In 1849 its founder became the first independent auditor of a public company, Britain's Great Western Railway. Its auditors check companies' financial reports for errors and fraud before investors rely on them, while its consultants design strategy, install business software, and defend clients against cyberattacks. Clients pay fees for each audit or project, and each country's Deloitte firm is a separate business owned by its local partners. Deloitte was founded in London in 1845 and is based in New York.

Company size: 10,001+
Company stage: Late Stage VC
Total funding: $17.1M
Headquarters: New York, NY
Founded: 1845

Recently Posted Jobs

Explore more opportunities at Deloitte

See more jobs