Fullstack LLM/ML Engineer
ChatPlace is a SaaS platform for promotion and sales through content on Instagram, Telegram, and TikTok. We create tools for content generation and audience interaction automation: AI agents, chatbots, auto-funnels, gamification, and other mechanics that help businesses grow without a large budget or technical complexity.
We are looking for a Fullstack LLM / ML Engineer to help build and develop production-ready LLM systems: ensuring content and dialogues are stable, predictable, measurable in quality, and understandable in operation.
Responsibilities:
In general: Design, develop, and implement (from front-end to back-end) LLM systems for content generation and audience interaction automation.
In detail:
- Act as a Feature Owner: independently design, develop, and bring to release the full stack of solutions for AI agents, including:
- Assembling the "agent architecture": context/memory/state, rules, knowledge base, routing, fallback.
- Developing necessary Backend logic (APIs, services) and integrating with Frontend parts of the product for rapid launch of new features.
- Build quality control: golden set, quality rubrics for different scenarios, regression tests, A/B testing.
- Establish industrial monitoring, tracing, and logging systems for quick understanding of "why it got worse" through logs and traces.
- Independently bring features to production as much as possible: responsible for API contracts, error handling (retries, timeouts), provider limits, pipeline versions, and feature flag management.
- Iteratively improve the system based on feedback from expert creators and service users.
Our Ideal Candidate:
- 4+ years of experience in Applied LLM / ML Engineering with proven experience in End-to-End development of production-ready systems and features.
- Mandatory experience in bringing LLM/GenAI solutions to a production system with a Fullstack approach: from developing APIs and services (backend) to final integration into the user interface (frontend integration).
- Proficient in Python (or Node) at the level of developing production-ready Backend services and LLM pipelines.
- Understanding of Frontend development (at the level of working with JS frameworks) and the ability to implement the client-side of LLM features.
- Deep understanding of engineering fundamentals: APIs, retries/timeouts, rate limits, logging, versioning, feature flags.
- Ability to think product-first and make technical decisions with a high degree of autonomy.
- Will be a plus: Agentic workflows (state/memory/routing/policy), RAG / knowledge base, cost/latency optimization, multilingual scenarios, workflow tools (n8n/Make).
Format and Conditions:
- Salary is discussed individually, depending on experience and level of autonomy.
- Remote work within a strong engineering team. Flexible schedule. Focus on results with a reasonable level of freedom.
- High level of autonomy and influence on key product directions: content and agents.
- Fast-growing product with an entry into the global market.
- Various employment formats, including work outside of the Russian Federation.
- We are an accredited IT company.
