
Senior ML Engineer
- Warszawa, mazowieckie
- Stała
- Pełny etat
- Integrate and optimize applications using LLM provider APIs (e.g. OpenAI Chat Completions), including model/parameter selection, structured output, function calling, etc.
- Design and refine prompts with few-shot, chain-of-thought, context crafting, and prompt chaining techniques.
- Benchmark and evaluate models (e.g., reasoning vs. non-reasoning) using custom eval sets and automated testing frameworks.
- Build and monitor RAG pipelines, implement summarization, chat with data and other use cases.
- Develop robust backend services in .NET and Python, working with SQL, REST APIs, and integrating with LLM services.
- Implement LLM tracing, monitoring, and logging for observability.
- Apply prompt security best practices, including injection protection and guardrails.
- Collaborate across teams to build agentic workflows, and support ETL/data transformations for AI readiness.
- 1-2+ years demonstrable experience in developing Generative AI applications.
- Proven hands-on experience with OpenAI APIs, model selection, and LLM capabilities
- Proven hands-on experience with prompt engineering, including structured prompts, function calls, and evaluation techniques.
- Experience with RAG and building LLM-centric workflows
- 3+ years of experience as a software developer
- Strong backend development skills in .NET (C#) and SQL
- Proficiency in Python; familiarity with JavaScript
- Experience with Docker, Kubernetes, and RESTful APIs
- Familiarity with Azure, particularly AKS, ACR, and containerized app deployment
- English - fluent speaking, reading and writing
- Experience with Azure OpenAI, PromptFlow, Azure AI Services, and Azure ML
- Familiarity with CosmosDB, KQL, Azure Log Analytics, App Insights
- LLM use cases: Text-to-SQL, chat over DBs
- Exposure to other LLM APIs (Anthropic, Mistral, Cohere, etc.)
- Prompt caching/compression, LLM output validation
- Familiarity with Redis caching
- Frontend experience with React and Next.js