🧠 Tech Level: Senior

🗣 Language Proficiency: Upper-Intermediate

👥 FTE: 1

🧾 Employment type: Full time

🌍 Candidate Location: Poland

🕐 Working Time Zone: CET (European time zone with occasional cross-region meetings)

🚀 Start: asap

🧭 Planned Work Duration: 6 months (possible extension)

👥 Customer Description:

Our client is a leading global management consulting firm.

🧩 Project Description:

The project focuses on building and iterating on GenAI proof-of-concepts for knowledge capture and curation.

The engineer will work across the complete AI application lifecycle, including prototyping, deployment, observability, optimization, and production scaling of enterprise AI solutions.

⚙️ Project Phase:

active development

🤝 Soft Skills:

• Excellent communication skills with the ability to explain complex AI concepts to both technical and non-technical stakeholders

• Strong analytical and problem-solving mindset

• Demonstrated ability to lead technical initiatives

💡 Hard Skills / Must Have:

• 6+ years of software engineering experience, including backend systems, APIs, distributed systems.

• 3+ years of experience with production GenAI or LLM applications

• Strong expertise in Python

• Experience building scalable APIs, microservices, and cloud-native applications.

• Strong understanding of production system design, scalability, resiliency, and observability principles.

• Hands-on experience with:LLM APIs and RAG.

• AI agents and tool-calling architectures.

• Multi-agent orchestration systems.

• Prompt engineering and prompt; optimization.

• Embedding models and vector databases.

• Experience working with multiple foundation model providers and open-source LLM ecosystems.

• Experience with cloud platforms such as AWS, Azure, or GCP.

• Experience integrating GenAI systems with enterprise platforms, APIs, and data ecosystems.

✨ Hard Skills / Nice to Have:

• Experience with frameworks such as LangChain, LangGraph, LlamaIndex, CrewAI, Semantic Kernel, AutoGen, or similar.

• Experience with model fine-tuning, PEFT, LoRA, and open-source LLM deployment.

• Experience with vector databases such as Pinecone, Weaviate, Chroma, FAISS, Milvus, or pgvector.

• Experience with Docker, Kubernetes, Ray, MLflow, Airflow, or Temporal.

• Experience with AI observability and evaluation platforms such as LangSmith, Weights & Biases, Arize, Helicone, Phoenix, or similar.

📌 Responsibilities:

• Design, develop, and deploy scalable GenAI applications using LLMs, RAG, AI agents, and workflow orchestration frameworks

• Build production-grade AI systems integrating structured and unstructured enterprise data

• Architect and optimize end-to-end AI pipelines

• Develop AI-powered copilots, assistants, automation workflows, and autonomous agent systems

• Design hybrid AI systems combining deterministic workflows with autonomous agent behavior

• Build multi-agent orchestration workflows

• Implement tracing, telemetry, observability, and monitoring

• Develop automated evaluation pipelines and testing frameworks

• Improve reliability through retrieval optimization and AI safety mechanisms

• Optimize inference cost, latency, throughput, and scalability

• Own AI systems from prototype to production

• Collaborate with stakeholders, product managers, platform teams, and data engineers

• Stay current with advances in LLMs, agentic AI, multimodal systems, and AI infrastructure

🧪 Technology Stack: Python, FastAPI, SQL, Snowflake, Streamlit, React (light), LangChain, LangGraph, LLM APIs via internal gateway, vector databases, Docker, Kubernetes, AWS

📝 Additional notes:

The candidate must be employed in client's company at 0.125 FTE under UoP (employment contract) and additionally under a service contract (B2B or mandate contract). Payment terms — up to 60 days. Work will be performed using client-provided equipment.

📩 Ready to Join?
We look forward to receiving your application and welcoming you to our team!