AI Engineer (Agents) Middle / Senior
We are a product team building a platform focused on virtual AI agents for communication automation. We work fast, without excessive bureaucracy, experiment a lot, and implement new approaches. We are currently strengthening our agent systems direction and are looking for an engineer who understands how it works not only from the outside but also "under the hood".
What you will do:
- Develop and enhance voice and text AI agents (pipeline: STT → LLM → TTS)
- Build and improve agent scenarios: prompting, tool use, orchestration
- Optimize pipeline latency, response quality, and stability
- Fine-tune and evaluate LLM and speech models for real-world use cases
- Integrate AI components into production (C# / SIP / RTP stack)
- Research and implement new models, frameworks, and approaches
Our stack:
- Python, C#
- Whisper (STT), Qwen / LLaMA / Mistral (LLM), Kokoro (TTS)
- LangChain / LlamaIndex
- vLLM / Ollama / llama.cpp
- SIP / RTP, Windows / Linux
What we expect:
- 2+ years of experience in production AI/ML
- Understanding of LLMs: prompting, RAG, fine-tuning
- Experience with agent systems
- Understanding of how models and pipelines are structured
- Experience with speech (STT / TTS) - will be a strong plus
- Ability to evaluate model quality end-to-end
- Experience with on-premise inference (local deployment, quantization, latency)
- Proficient work with Linux and/or Windows
What is important:
- Interest in agent systems and AI
- Readiness to work in a dynamic environment: many diverse tasks
- Ability to independently figure things out and bring solutions to production
Will be a plus:
- HuggingFace ecosystem
- Experience in Telecom / VoIP
- Agentic AI (tool use, multi-agent systems)
Work format:
- Relocation to Tashkent for the launch period (until September)
- Afterwards - full remote
- Flexible collaboration format
