Full-timeEngineering

TripActions

Senior Machine Learning Engineer- LLMs & Self-Hosted AI

Tel-Aviv, Israel

Posted

12d ago

Type

Full-time

Location

Tel-Aviv, Israel

Job Overview

We are looking for a highly skilled Senior ML Engineer to lead our transition from third-party LLM APIs to a fully self-hosted ecosystem by fine-tuning high-performance, domain-specific models . Our core product is an advanced, agentic support chatbot capable of complex reasoning, API tool calling, database lookups, and orchestrating specialized LLMs for specific tasks. What You’ll Do: • Model Fine-Tuning: Design and execute fine-tuning strategies to improve model accuracy on specific domain tasks and tool-calling execution. • Agentic Workflows: Develop and refine the chatbot's agentic capabilities, ensuring reliable tool-use, routing, and interactions between massive LLMs and specialized SLMs. • Inference Optimization: Deploy and manage large-scale models using high-performance inference engines (like vLLM) to ensure low latency and high throughput for our agentic chatbot. • Rigorous Evaluation: Build comprehensive offline and online evaluation frameworks to constantly measure model performance and business impact through structured A/B testing. What We’re Looking For: Core Engineering & AI Frameworks • Deep experience with PyTorch and the Hugging Face ecosystem. • Strong Data Engineering skills: data manipulation, synthetic data generation, and active learning/margin-sampling. • High proficiency with AI-assisted development workflows (e.g., Claude Code, Cursor, Codex) to accelerate development. LLMs & Agents • Strong fundamental understanding of LLM architectures, attention mechanisms, and generation parameters. • Hands-on experience building Agentic systems (ReAct, function/tool calling, RAG). • Expertise in fine-tuning strategies (e.g., SFT, RLHF, DPO) and parameter-efficient techniques (PEFT/LoRA). Bonus Points • Alignment Techniques: Experience with RLHF and DPO strategies for future reasoning-model development. • Containerization & Orchestration: Experience with Ray for orchestrating large-scale model deployments across multi-GPU clusters. • Model Quantization: Experience with memory optimization techniques like AWQ, GPTQ, or GGUF to fit 70B models efficiently onto hardware. • API Development: Proficiency in building robust, asynchronous microservices using FastAPI to serve model requests. • Experience with core MLOps practices , including dataset versioning (e.g., DVC), experiment tracking (e.g., Weights & Biases, MLflow), and model registries .

Core Requirements

Engineering