{"id":51648,"title":"Senior AI Researcher: LLM post-training for hallucination reduction (f/m/d)","company":"Aleph Alpha","city":"Heidelberg","region":"Baden-Württemberg","location":"Heidelberg, Heidelberg, Baden Würtemberg, Germany","work_model":"hybrid","employment_type":"full_time","employment":["full_time"],"roles":["data_science"],"visa":"not_mentioned","relocation":"not_mentioned","posted_at":"2026-10-14T10:15:36.986000+00:00","tools":["LLM","RAG","Python","PyTorch"],"seniority":"senior","years_experience_min":null,"german_requirement":"not_mentioned","german_level":"unspecified","english_requirement":"required","english_level":"unspecified","team_language":"unknown","confidence":0.4,"method":"rules","language_badge":"Not stated","language_evidence":null,"requirements_snippet":"Hands-on experience fine-tuning or post-training LLMs using modern distributed training frameworks. Track record of research or implementation in at least one of the following domains: Hallucination mitigation / truthfulness …","url":"https://jobs.ashbyhq.com/alephalpha/fce0b58f-e95a-45bc-9ca5-b47b1c3cbabd","source":"ashby","agency":null,"description_text":"Who we are\nAleph Alpha’s mission is to deliver sovereign, human-centric AI to governmental institutions and large enterprises. To that end, we deliver category-defining AI innovation that enables open, accessible, and trustworthy deployment of GenAI in industrial applications. Our organization develops foundational models and next-generation methods that make it easy and affordable for Aleph Alpha’s customers to increase productivity in development, engineering, logistics, and manufacturing processes.\n\nAbout the role\nWe are looking for a (Senior) AI Researcher to join our hallucination reduction capability team to push the boundaries in LLM post-training (SFT and RL).\nWe're one of the few places in Europe training foundation models from scratch. You will be part of a team of (senior) researchers and PhD interns doing cutting-edge research across pre-, mid- and post-training, grounding and specialized models with hundreds of GPUs at our disposal.\n\nWhat will you do\n• Core Research & Development: Design, execute, and scale post-training methodologies (SFT, RL) specifically aimed at eliminating model hallucinations and making them grounded in evidence.\n• Uncertainty & Reliability: Research and implement techniques in uncertainty estimation, calibration, self-consistency, and self-correction mechanisms to enable models to identify and signal when they “don't know”.\n• Post-Training Pipelines: Build and optimize high-throughput, distributed fine-tuning and training pipelines across multi-node GPU clusters.\n• Evaluation & Benchmarking: Design and implement rigorous evaluation methods to benchmark hallucination rates, truthfulness, and reasoning accuracy.\n• Technical Ownership: Drive research projects independently from initial hypothesis to scalable production implementation and technical reports.\n\nQualifications\n• Hands-on experience fine-tuning or post-training LLMs using modern distributed training frameworks.\n• Track record of research or implementation in at least one of the following domains:\n• Hallucination mitigation / truthfulness alignment / grounding in RAG\n• Uncertainty estimation, or out-of-distribution detection\n• Retrieval-Augmented Generation evaluation / alignment, refusal behavior calibration, or claim verification\n• Strong programming skills (Python & PyTorch).\n\nCompensation and Benefits\n• Become part of an AI revolution!\n• 30 days of paid vacation\n• Access to a variety of fitness & wellness offerings via Wellhub\n• Mental health support through nilo.health\n• Substantially subsidized company pension plan for your future security\n• Subsidized Germany-wide transportation ticket\n• Budget for additional technical equipment\n• Flexible working hours for better work-life balance and hybrid working model\n• JobRad® Bike Lease","responsibilities_text":"We are looking for a (Senior) AI Researcher to join our hallucination reduction capability team to push the boundaries in LLM post-training (SFT and RL).\nWe're one of the few places in Europe training foundation models from scratch. You will be part of a team of (senior) researchers and PhD interns doing cutting-edge research across pre-, mid- and post-training, grounding and specialized models with hundreds of GPUs at our disposal.\nWhat will you do\n• Core Research & Development: Design, execute, and scale post-training methodologies (SFT, RL) specifically aimed at eliminating model hallucinations and making them grounded in evidence.\n• Uncertainty & Reliability: Research and implement techniques in uncertainty estimation, calibration, self-consistency, and self-correction mechanisms to enable models to identify and signal when they “don't know”.\n• Post-Training Pipelines: Build and optimize high-throughput, distributed fine-tuning and training pipelines across multi-node GPU clusters.\n• Evaluation & Benchmarking: Design and implement rigorous evaluation methods to benchmark hallucination rates, truthfulness, and reasoning accuracy.\n• Technical Ownership: Drive research projects independently from initial hypothesis to scalable production implementation and technical reports.","requirements_text":"• Hands-on experience fine-tuning or post-training LLMs using modern distributed training frameworks.\n• Track record of research or implementation in at least one of the following domains:\n• Hallucination mitigation / truthfulness alignment / grounding in RAG\n• Uncertainty estimation, or out-of-distribution detection\n• Retrieval-Augmented Generation evaluation / alignment, refusal behavior calibration, or claim verification\n• Strong programming skills (Python & PyTorch).\nCompensation and Benefits\n• Become part of an AI revolution!\n• 30 days of paid vacation\n• Access to a variety of fitness & wellness offerings via Wellhub\n• Mental health support through nilo.health\n• Substantially subsidized company pension plan for your future security\n• Subsidized Germany-wide transportation ticket\n• Budget for additional technical equipment\n• Flexible working hours for better work-life balance and hybrid working model\n• JobRad® Bike Lease","status":"open","duplicate_of":null,"first_seen":"2026-11-02T14:18:15.676236+00:00","responsibilities_summary":null,"requirements_summary":null,"all_tools":["LLM","RAG","Python","PyTorch"],"posting_language":"en","evidence":[],"years_experience_max":null,"mobility_evidence":[],"model_version":"rules-8","english_badge":"English required","company_id":115}