Senior AI Researcher: LLM post-training for hallucination reduction (f/m/d)

AlephAlpha · Heidelberg, Berlin · Posted Oct 14, 2026


Transparency

Dead

Online for 5 weeks and never reposted. Jobs this old or reposted this often rarely lead to a hire. It may be filled already.

First seen
Nov 12, 2026
Offered for
37 days

Overview

Category
AI & machine learning
Employment type
Permanent
Workplace type
Hybrid
Country
Germany
Seniority
Senior
Schedule
Full time
Salary
Not listed

Key skills

Post‑training LLM methods
Design and scale SFT and RL techniques to reduce hallucinations in large language models.
Uncertainty and reliability
Implement uncertainty estimation, calibration, self‑consistency and self‑correction to detect unknowns.
Distributed fine‑tuning pipelines
Build high‑throughput multi‑node GPU pipelines for large‑scale post‑training.
Evaluation and benchmarking
Create rigorous tests to measure hallucination rates, truthfulness and reasoning accuracy.
Python & PyTorch programming
Develop research code and production prototypes using Python and PyTorch.

Key phrases

  • LLM post-training
  • hallucination reduction
  • SFT
  • RL
  • foundation models
  • uncertainty estimation
  • calibration
  • self-consistency
  • self-correction mechanisms
  • distributed fine-tuning
  • multi-node GPU clusters
  • hallucination rates
  • truthfulness
  • reasoning accuracy

From the posting

Who we are

Aleph 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.

About the role

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).

We'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.

What will you do

  • Core Research & Development: Design, execute, and scale post-training methodologies (SFT, RL) specifically aimed at eliminating model hallucinations and making them grounded in evidence.

  • 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”.

  • Post-Training Pipelines: Build and optimize high-throughput, distributed fine-tuning and training pipelines across multi-node GPU clusters.

  • Evaluation & Benchmarking: Design and implement rigorous evaluation methods to benchmark hallucination rates, truthfulness, and reasoning accuracy.

  • Technical Ownership: Drive research projects independently from initial hypothesis to scalable production implementation and technical reports.

Qualifications

  • 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 alignment / grounding in RAG

    • Uncertainty estimation, or out-of-distribution detection

    • Retrieval-Augmented Generation evaluation / alignment, refusal behavior calibration, or claim verification

  • Strong programming skills (Python & PyTorch).

Compensation and Benefits

  • Become part of an AI revolution!

  • 30 days of paid vacation

  • Access to a variety of fitness & wellness offerings via Wellhub

  • Mental health support through nilo.health

  • Substantially subsidized company pension plan for your future security

  • Subsidized Germany-wide transportation ticket

  • Budget for additional technical equipment

  • Flexible working hours for better work-life balance and hybrid working model

  • JobRad® Bike Lease

More jobs at AlephAlpha

Senior AI Researcher- Pre-training (f/m/d)

AlephAlpha · 6 days ago | Heidelberg, Berlin | Hybrid · Senior · Full time

Create CV

AI Researcher - Pre-training (f/m/d)

AlephAlpha · Last week | Berlin, Heidelberg | On-site · Mid level · Full time

Create CV

Senior AI R&D Engineer - Performance - Pre-training (f/m/d)

AlephAlpha · Last month | Heidelberg | Hybrid · Senior · Full time

Create CV
See all 4 jobs at AlephAlpha