Company: Netbell
🔹 What you will do:
- Integrate LLMs into products and services (API, backend, data processing pipelines);
- Develop and optimize prompts, CoT, system instructions;
- Evaluate response quality (metrics + human eval);
- Configure guardrails: security, filtering, compliance;
- Build RAG systems:
- data indexing;
- working with vector databases;
- optimizing search and generation;
- Optimize inference (cost, latency, batching, caching, quantization);
- Participate in architectural decisions with the product and ML team;
- Research and implement new approaches and models;
- If necessary: work with multimodal models (text, images, documents).
🔹 What is important:
- Solid Python skills;
- Experience with LLMs in production (not just pet projects);
- Understanding of:
- prompt engineering;
- RAG approaches;
- model quality evaluation;
- Experience deploying ML/LLM solutions (Docker, Kubernetes, cloud);
- Working with vector databases.
🔹 Will be a plus:
- Fine-tuning / PEFT (LoRA, adapters);
- RLHF or synthetic data generation;
- Experience with:
- LangChain;
- LlamaIndex;
- Hugging Face;
- Inference optimization (vLLM, TensorRT, ONNX);
- Experience with multimodal models;
- Publications / open-source / pet projects;
- Hackathon participation;
- Understanding of product metrics.
🔹 What we offer:
- Full remote work
- Accredited IT company
- Interesting product, modern stack, microservice architecture
- Well-known clients from the TOP-10 in their segments
- Skill development under the guidance of leads with 8+ years of experience
- Decent salary based on interview results + quarterly company fund with bonuses for top employees
- Opportunity to take on additional tasks for corresponding compensation
- Bonuses for mentoring junior employees
- Quarterly bonuses and gifts for top employees
- Refer a friend and receive a generous reward for the recommendation
Contacts: recruiter contact
