Senior AI Engineer

Náplň práce

Project overview

For our client we are enriching our existing development team which will be responsible for further development of one of our most successful products. The product is an integrated delivery platform that leverages the depth and breadth of real-world engagements’ experience. It also enables cross-team collaboration, real-time transparency and insightful decision-making.

Responsibilities:

· Architect end -to-end LLM -based pipelines using RAG, embeddings, and orchestration layers.
· Design multi -agent systems using LangChain, LangGraph, CrewAI, or AutoGen, emphasizing modularity and scalability.
· Evaluate model options (e.g., OpenAI, Azure OpenAI) based on tradeoffs in performance, cost, and capabilities.
· Define embedding strategies, context windows, and prompt structures for complex reasoning tasks.
· Build chunking and ingestion pipelines for PDFs and unstructured documents using Python SDKs (LangChain, pyPDF, RecursiveCharacterTextSplitter).
· Integrate and deploy vector stores (e.g., Azure AI Search, FAISS, postgres, chromadb ) with semantic search and reranking techniques.
· Implement CI/CD pipelines, test coverage, and API integrations (e.g., via Postman, GitHub Actions).
· Build and maintain well -structured, reusable Python classes for LLM tools, pipelines, agents, and evaluation modules.
· Debug and optimize complex, distributed Python systems involving multiple services and third -party APIs.
· Develop and maintain Jupyter Notebooks for prototyping, analysis, and executive storytelling, balancing clarity and depth.
· Create and deploy Docker containers for reproducible development, testing, and production environments.
· Work with CI/CD pipelines (GitHub Actions or similar) to ensure high -quality, testable code.
· Use vibe coding tools (Cursor, GitHub Copilot) to accelerate development while ensuring security, compliance, and reusability.
· Develop and orchestrate autonomous agents with well -defined roles, tools, and memory -sharing strategies.
· Implement observer and fallback agents to enhance system resilience and reduce hallucinations.
· Use telemetry and observability tools (e.g., Data dog, Lang Fuse) to monitor, debug, and optimize performance.
· Define and track evaluation metrics for GenAI and RAG systems (faithfulness, precision, recall, F1, semantic similarity).
· Use sklearn, NumPy, and Ragas evaluation loops to validate model performance and content grounding.
· Implement output schema validation, prompt constraints, and quality assurance processes for enterprise -readiness.
· Build interactive prototypes using Streamlit, LangFlow, or Jupyter Notebooks to demonstrate capabilities and insights.
· Translate complex models into clear, explainable insights for executive stakeholders.
· Lead design sessions and mentor developers on AI best practices and tooling.

Predpoklady a zručnosti

Skills Required:

· 8+ years of experience in software engineering, with at least 3+ years focused on AI/ML, NLP, or LLM -based applications.

· Expert -level proficiency in Python, with a strong focus on building and debugging modular, class -based code for reusable, production -grade systems.

· Proven experience designing and deploying GenAI solutions using prompt engineering, embedding -based retrieval, and multi -agent orchestration patterns.

· Deep hands -on experience with modern AI/LLM frameworks including LangChain, LangGraph, CrewAI, AutoGen, and Hugging Face.

· Demonstrated ability to ingest, chunk, and semantically index large -scale unstructured data (e.g., PDFs, HTML, JSON) using LangChain, embedding models, and custom pipelines.

· Proficient in deploying and querying vector databases such as Azure AI Search, FAISS , or Postgres with pgvector for semantic search applications.

· Strong working knowledge of Jupyter Notebooks, Docker, GitHub, and RESTful API integration to accelerate development and prototyping workflows.

· Familiarity with DevOps and CI/CD pipelines (e.g., GitHub Actions) to enable rapid iteration, testing, and deployment of AI pipelines.

· Skilled in evaluating LLM and RAG pipeline performance using metrics like semantic similarity, precision, recall, and faithfulness with tools such as sklearn, NumPy, and RAGAS.

· Hands -on experience implementing observability and telemetry using platforms like LangFuse , Datadog, or custom logging/tracing solutions.

· Comfortable working with AI -powered developer tools such as GitHub Copilot, Cursor, and other vibe coding assistants to enhance velocity and maintainability.

Preferred Qualifications

· Experience with multimodal LLMs, vision -language models, or tool -augmented inference.

· Understanding of reasoning models, ReAct -style prompting, and planner -executor agents.

· Experience with agile ceremonies, sprint planning, and cross -functional delivery teams.

· Demonstrated ability to evaluate and compare multiple RAG pipelines using structured and human -in-the-loop evaluation methods.

· Strong communication skills — able to interface with engineering and executive audiences alike.

Ďalsie informacie

Seniority: Senior

Location: 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 (2-6 pm CET)?: Minimum 2-6pm CET, preferred 2

Language: EN

Start: ASAP

O spoločnosti

Technology and consulting software company.