Research Engineer, Multi-Domain Alignment (SLM)

Indian AI Research Organization (IAIRO); Bandon; On-site; EUR 90,000 - 140,000; Full time

Job summary

Indian AI Research Organization (IAIRO) is seeking a Research Engineer to join the Alignment team to advance Sovereign AI by developing compact, right-sized models and robust safety frameworks.

You will bridge base pretraining and deployment, architect behavioral logic and safety for multimodal SLMs, and work across domains such as Legal, Healthcare, and Industrial Robotics to maintain alignment with human intent and cultural values.

Qualifications

• Master's or PhD in Computer Science, ML, or equivalent practical experience in training large-scale models.
• Expertise in Python and PyTorch within the Hugging Face ecosystem (Transformers, TRL, PEFT, Accelerate).
• Proven Alignment Track Record: RLHF, Direct Preference Optimization (DPO), and Constitutional AI.
• Scaling Knowledge: Deep understanding of Scaling Laws and the Alignment Tax for compute-constrained environments.
• Multimodal familiarity: Experience aligning models that process text, visual, and sensor data.

Responsibilities

• Frontier Alignment Research: Design and implement scalable alignment pipelines (SFT, DPO, PPO) to optimize 1B-7B parameter models for high-stakes, domain-specific tasks.
• Advanced Preference Modeling: Architect reward models and preference datasets that capture nuanced domain expertise.
• Multi-domain Synthesis: Develop techniques to mitigate alignment drift and catastrophic forgetting when models are specialized across disparate industries.
• Evaluation & Red-Teaming: Create automated benchmarking suites and adversarial testing frameworks to validate model robustness.
• Open Source & Transparency: Contribute to the community by open-sourcing high-quality code and reproducible research.

Skills

Python

PyTorch

HuggingFace

RLHF

DPO

Constitutional AI

Scaling Laws

Multimodal models

Education

Master's or PhD in Computer Science / ML

Tools

Transformers

TRL

PEFT

Accelerate

vLLM

TensorRT

CUDA

Job description

About The Role

IAIRO is seeking a Research Engineer to join our Alignment team. We are committed to advancing the frontier of Sovereign AI by developing compact, "right-sized" models that are as steerable and reliable as their massive counterparts.

In this role, you will bridge the gap between base pretraining and real-world deployment. You won't just be fine-tuning checkpoints; you will be architecting the behavioral logic and safety frameworks for a new class of multimodal SLMs. Your work will focus on multi-domain alignment, ensuring our models can transition seamlessly between specialized fields—such as Legal, Healthcare, and Industrial Robotics—while maintaining rigorous adherence to human intent and cultural values.

Core Responsibilities

• Frontier Alignment Research: Design and implement scalable alignment pipelines (SFT, DPO, PPO) to optimize 1B-7B parameter models for high-stakes, domain-specific tasks.


• Advanced Preference Modeling: Architect reward models and preference datasets that capture nuanced domain expertise, moving beyond generic "helpfulness" to expert-level reasoning.


• Multi-domain Synthesis: Develop innovative techniques to mitigate "alignment drift" and "catastrophic forgetting" when models are specialized across disparate industries (e.g., ensuring a model stays factually grounded in domain contexts while remaining flexible in creative ones).


• Evaluation & Red-Teaming: Devise rigorous, automated benchmarking suites (LLM-as-a-judge) and adversarial testing frameworks to validate model robustness in "out-of-distribution" scenarios.


• Open Source & Transparency: Contribute to the broader AI community by open-sourcing high-quality code and producing reproducible research that impacts the Sovereign AI ecosystem.

Required Skills & Experience

• Master's or PhD in Computer Science, ML, or equivalent practical experience in training large-scale models.


• Expertise in Python and PyTorch, specifically within the Hugging Face ecosystem (Transformers, TRL, PEFT, Accelerate).


• Proven Alignment Track Record: Significant experience with RLHF (Reinforcement Learning from Human Feedback), Direct Preference Optimization (DPO), and Constitutional AI.


• Scaling Knowledge: A deep understanding of Scaling Laws and the "Alignment Tax - knowing how to maximize performance in compute-constrained environments.


• Multimodal Familiarity: Experience aligning models that process not just text, but visual and sensor-based data.

Bonus Qualifications

• Publication Record: Research results published at leading venues such as NeurIPS, ICML, ICLR, or MLSys.


• Synthetic Data Engineering: Experience building high-fidelity synthetic data pipelines to improve multi-step reasoning and logic.


• Hardware Awareness: Familiarity with optimizing inference engines (vLLM, TensorRT-LLM) or writing custom kernels (Triton/CUDA) for deployment on edge devices.