Senior AI Engineer (Product Neuro Forge Team)

Stack

Responsibilities

• ▹Own AI/ML features end-to-end: research, prototype, production, monitoring and iteration
• ▹Design and build LLM-powered features on reviews and ratings data: feedback categorization, summarization, reply generation, semantic search, anomaly detection, conversational and agentic scenarios
• ▹Work with commercial LLM APIs (OpenAI, Anthropic, Google) and open-source models (Llama, Mistral, Qwen, etc.): model selection, adaptation, fine-tuning and deployment
• ▹Build and maintain pipelines for model training, fine-tuning and quality evaluation: datasets, metrics, offline evals, LLM-as-a-judge, A/B tests
• ▹Develop RAG and semantic search capabilities: embeddings, vector storage, retrieval quality
• ▹Optimize quality, latency and cost of LLM inference in production
• ▹Track state-of-the-art in NLP/LLM, run experiments and POCs, and turn promising ones into product features
• ▹Collaborate with backend, product and platform teams; contribute to overall system architecture; write efficient, testable, secure and documented code

Requirements

• ▹5+ years of software development experience; strong production Python (asyncio)
• ▹3+ years of hands-on ML/NLP experience with models shipped to production
• ▹Practical experience with LLMs: prompt engineering, RAG, fine-tuning open-source models (LoRA/PEFT), commercial APIs and self-hosted models
• ▹Experience building model quality evaluation processes: metrics, eval datasets and pipelines, A/B testing
• ▹Confidence with the PyTorch and Hugging Face ecosystem (transformers, datasets, PEFT)
• ▹Proficiency in FastAPI for API development
• ▹Strong SQL skills (MySQL or PostgreSQL), experience with ORM frameworks (preferably SQLAlchemy)
• ▹Experience with unit testing (pytest)
• ▹Upper-intermediate English or higher

Nice to have

• ▹Experience serving open-source LLMs in production (vLLM, TGI, Triton) and working with GPU infrastructure
• ▹Experience with vector databases (e.g. pgvector)
• ▹Experience with agentic and orchestration frameworks (LangChain, LangGraph) and eval/observability tooling (MLflow, Langfuse)
• ▹Experience with data processing pipelines and automation (e.g. Airflow, Prefect)
• ▹Experience with cloud services (AWS), NoSQL databases (MongoDB), message brokers (RabbitMQ, Kafka)
• ▹Classical ML/NLP background (text classification, clustering, topic modeling)
• ▹Open-source contributions, publications or pet ML projects

Soft skills

What we offer

• ▹Full-time remote job, with monthly All hands welcome in hubs: Helsinki, Belgrade, Tbilisi, Batumi, Yerevan
• ▹Paid vacation and sick leaves
• ▹Days off for special occasions by prior agreement
• ▹Generous social benefits package including health insurance, equipment reimbursement, home office bonus and more
• ▹Stock options bonus according to the employee stock ownership plan
• ▹Executive-level visibility into how the company is run and performing
• ▹Dedicated support and fast-track onboarding

About the company

AppFollow is an app review management and ASO platform that helps app developers, product managers, marketing and customer support teams manage their data, increase average rating and improve app store rankings. Ratings and reviews are its core data, and AI is how it turns them into value for customers.