Machine Learning Engineer (Generative AI + Full-Stack Development)

Machine Learning Engineer (Generative AI + Full-Stack Development)

Stack: .NET + Python + React

Location: Riga (full-time). Relocation support for international candidates.

Company: JE Riga — full-cycle custom software product development since 2007, with deep domain expertise in reinsurance, insurance, financial services, and more.

Role

We’re looking for a Machine Learning Engineer with full-stack expertise (.NET + Python + React) who is passionate about Generative AI and modern agentic systems. You’ll design, build, and deploy scalable applications end-to-end while also working on AI-driven features (agents, RAG, prompt engineering, evals & observability). If you enjoy both hands-on full-stack development and pushing Generative AI into production, this is the right role for you.

Responsibilities

• Build and maintain enterprise web applications with .NET (C#), Python, and React/TypeScript.
• Develop backend services in .NET and Python (APIs, agentic workflows, background workers).
• Generative AI & Agent Systems:
• Design agentic workflows (tool/function calling, memory, planning).
• Build RAG pipelines and context retrieval mechanisms.
• Develop and version prompts; maintain prompt libraries and guardrails.
• Integrate with Generative AI providers (Azure OpenAI/OpenAI, Anthropic, Mistral, etc.).
• Implement evaluations (LLM-as-judge, golden datasets, rubric-based scoring, online A/B).
• Add observability & safety (latency, quality, cost tracking, prompt-injection defenses, data privacy).
• Work with relational and vector databases (schema design, embeddings, indexing, similarity search).
• Maintain high standards in code quality, testing (unit, integration, prompt evals), and CI/CD.
• Collaborate with stakeholders to translate requirements into reliable features and metrics.

Requirements

• Full-stack engineering experience with:
• .NET (C#) for backend services and APIs.
• Python for AI/ML utilities, agentic systems, or backend services.
• React/TypeScript for frontend applications.
• Practical experience with Generative AI applications:
• Prompt engineering, structured output, tool/function calling, context management.
• Retrieval-Augmented Generation (RAG) design and optimization.
• Familiarity with frameworks like LangChain, Semantic Kernel, AutoGen, CrewAI, or Guidance.
• Experience with evals & observability frameworks (e.g., Langfuse, LangSmith, Phoenix, promptfoo, DeepEval, TruLens).
• Solid knowledge of SQL databases (SQL Server/PostgreSQL) and vector stores (pgvector, Pinecone, Qdrant).
• Competence with REST/GraphQL APIs, async programming, Git, and CI/CD pipelines.
• Cloud experience (Azure/AWS/GCP) and containerization (Docker, Kubernetes a plus).
• Strong communication skills in English.

Nice to Have

• Real-time features (SignalR/WebSockets/SSE) or distributed background workers.
• Experience with cost-aware AI design (token optimization, caching, model selection).
• AI security & compliance (data residency, provider review, safe tool access).
• Domain experience in insurance/finance or other data-intensive industries.

What We Offer

• A stable role with strong professional growth opportunities.
• Salary range: 3500-6000 EUR Gross per month, depending on experience.
• Supportive and collaborative team culture.
• Health insurance, flexible working hours, and modern office space.
• Company-sponsored certifications, training programs, and online courses.
• Relocation support for international candidates.