Senior AI Engineer

At DAC.digital, we are constantly growing our business. As part of our growth strategy, we are strengthening our strategic partnership with a company leveraging Generative AI to drive enterprise revenue and profit.

Key information:

Salary:

• 30 000 - 35 000 PLN net/month - pure B2B contract

• 26 000 – 30 500  PLN net/month – B2B contract (days off included)

It is vital that you have:

• fluency in English (min. C1);

• 5+ years in software/platform engineering with recent production LLM applications (not just prototypes);

• hands-on expertise with agentic frameworks (one or more of: LangGraph/LangChain Agents, AutoGen, CrewAI, LlamaIndex Agents, Semantic Kernel, Haystack Agents) and tool/function-calling patterns;

• strong RAG engineering across vector DBs, chunking/embedding strategies, metadata/search ranking, and grounding techniques;

• proven track record building observable, cost-aware, and secure LLM systems (tracing, evals, guardrails, secrets/IAM, PII handling);

• solid software engineering fundamentals: Python/TypeScript, async patterns, APIs, testing, CI/CD, containerization;

• clear communicator who can interface with clients and write crisp technical docs;

• working in agile methodologies (Scrum, Kanban);

• eager to learn and share knowledge.

Nice to have:

• Azure-first experience (Azure OpenAI, Azure AI Studio, Azure Functions/Container Apps/AKS, Private Link/VNet, Key Vault, Entra ID);

• cross-cloud exposure (AWS/GCP) and hybrid integrations; experience with enterprise connectors (SharePoint/OneDrive, ServiceNow, Salesforce);

• experience with structured output, constrained decoding, JSON Schemas, and program-of-thought planning.

Technology stack:

• Python

• TypeScript

• LLM

• LangGraph / LangChain Agents

• AutoGen, CrewAI

• CI/CD

You will be responsible for supporting our team in:

• design and implement modular AI agents with robust state management, memory, and routing using frameworks like LangChain/LangGraph, Microsoft AutoGen, CrewAI, LlamaIndex, Semantic Kernel, and Haystack;

• build reusable components including planners, tool registries, policy guards, and evaluators, integrated across clients and domains.

• connect agents to enterprise tools and data sources via APIs, webhooks, queues, and event-driven flows;

• implement retrieval-augmented generation (RAG) with vector and structured stores (pgvector, Pinecone, Weaviate, SQL, Graph), ensuring reliability with fallbacks, circuit breakers, and caching;

• define SLIs/SLOs, implement metrics, logging, and tracing (e.g., Langfuse, OpenTelemetry), and develop evaluation harnesses (automatic and human-in-the-loop) to measure task success, safety, and cost;

• productionize agents using CI/CD, feature flags, and canary deployments, optimizing cost-per-task and time-to-success.

• apply policy-as-code, data redaction, role/tenant isolation, and data minimization, collaborating with security teams to meet ISO 27001, SOC 2, NIST, HIPAA, and GDPR requirements;

• translate business processes into agentic solutions and create domain-specific agents and reusable templates for enterprise workflows.

What do we offer:

• possibility to work 100% remotely or on-site at our office in Gdańsk;

• b2b contract with included 30 days off;

• private Medical care;

• group insurance;

• pre-paid card or Sport Card;

• referral program;

• real Agile practices;

• employee well-being online platform;

• cafeteria benefits.