Agentic AI Engineer

Altimetrik Poland is a digital enablement company. We deliver bite-size outcomes to enterprises and startups from all industries in an agile way to help them scale and accelerate their businesses. We are unique in Poland's IT market. Our differentiators are an innovation-first approach, a strong focus on core development, and an ability to attack the challenging and complex problems of the biggest companies in the world.

We are looking for Agentic AI Engineer for our client- a global healthcare company that provides solutions to meet the evolving needs of patients worldwide. This role will be responsible for developing agentic solutions from prototype to production, combining LLMs, RAG, tool calling, orchestration frameworks, cloud AI services, and modern software engineering practices.

Your experience:

• 4+ years of experience in AI engineering, software engineering, data engineering, ML engineering, cloud engineering, or similar technical roles.

• Hands-on experience building GenAI applications, AI agents, RAG-based solutions, enterprise search, copilots, or LLM-powered workflow automation.

• Strong programming skills in Python, with experience building APIs, backend services, automation scripts, and reusable AI components.

• Strong understanding of LLMs, including prompt engineering, context engineering, model selection, temperature/top-p settings, context windows, embeddings, token usage, latency, and cost trade-offs.

• Practical experience with RAG architecture, including vector databases, embedding models, retrieval strategies, metadata filtering, document processing, grounding, and citation-based answers.

• Hands-on experience with multi-agent orchestration patterns, including supervisor-agent architectures, planner-executor workflows, routing agents, tool-using agents, evaluator agents, and human-in-the-loop agent flows.

• Experience implementing tool-calling capabilities, allowing agents to interact with databases, APIs, business applications, documents, and external services.

• Understanding of agent memory design, including session memory, long-term memory, vector-based memory, user context, conversation history, and governed memory retention.

• Experience implementing LLM and agent evaluation frameworks, including accuracy testing, grounding validation, hallucination detection, retrieval quality assessment, regression testing, adversarial testing, and user feedback integration.

• Understanding of model governance and responsible AI, including approved model usage, model selection criteria, evaluation evidence, security controls, auditability, and lifecycle management.

• Experience implementing guardrails for AI agents, including policy-based controls, restricted tool usage, approval gates, fallback flows, escalation paths, human-in-the-loop checkpoints, and kill-switch mechanisms.

• Experience with observability and tracing for agentic systems, including execution traces, tool-call monitoring, prompt/response metadata, token usage, latency, error handling, fallback analysis, and production debugging of multi-step workflows.

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

• Experience with cloud-native AI and agentic platforms such as AWS Bedrock Agents, AWS SageMaker, Azure OpenAI, Azure AI Agent Service, Azure AI Foundry, Semantic Kernel, or equivalent technologies.

• Understanding of enterprise data concepts, including structured data, unstructured data, semantic layers, data catalogues, metadata, data quality, and governed access.

• Experience with REST APIs, microservices, authentication, secrets management, logging, and cloud-native application patterns.

• Strong understanding of security and responsible AI principles, including role-based access, data privacy, prompt injection risks, hallucination control, content filtering, auditability, and safe agent execution.

• Ability to work with business stakeholders to understand use cases and translate them into practical AI agent capabilities.

• Strong communication skills and ability to collaborate with architects, data engineers, platform engineers, product owners, and business SMEs.

Nice to have:

• Experience with agent observability platforms or tracing tools for LLM applications, including LangSmith, Arize Phoenix, OpenTelemetry-based tracing, MLflow tracing, Databricks MLflow, cloud-native monitoring, or equivalent solutions.

• Experience designing human-in-the-loop AI systems, including approval workflows, exception management, escalation logic, user feedback capture, and controlled autonomy.

• Experience with model risk management, responsible AI, AI governance frameworks, prompt governance, model catalogues, evaluation reports, and audit-ready documentation.

• Experience designing tool registries, plugin architectures, MCP-based integrations, OpenAPI-based tools, schema-driven API invocation, and reusable agent capabilities.

• Experience with advanced multi-agent topologies, including supervisor agents, planner-executor agents, critic/evaluator agents, router agents, task-specific specialist agents, and autonomous workflow coordination.

• Experience designing tool registries and schema-driven integrations, using OpenAPI, JSON Schema, structured outputs, function-calling definitions, API contracts, and validation layers.

🔥We grow fast.

🤓We learn a lot.

🤹We prefer to do things instead of just talking about them.

If you would like to work in an environment that values trust and empowerment... don't hesitate, just apply!