Machine Learning Engineer - Generative Modeling

BehaviorAI; New York (NY); On-site; USD 160,000 - 200,000; Full time

Benefits offered by this job

Equity

Competitive pay

VC backing

Job summary

BehaviorAI in New York City is hiring a Machine Learning Engineer to join the founding team and build the next generation of AI models for understanding human behavior. This on-site role offers the chance to shape core technology with simulation and generative modeling as you scale training beyond real-world data collection.

You will design pipelines for real-world time-series data, iterate rapidly from proof-of-concept to production, and collaborate across ML, sensing, software, and product

Qualifications

• Strong foundation in deep learning with generative models or PINNs.
• Experience with PyTorch and real-world time-series data.
• Ability to move quickly from prototype to working systems.
• Ownership mindset and startup environment readiness.
• MS or PhD in a relevant field; exceptional undergraduates considered.

Responsibilities

• Design, build, and validate simulation and generative modeling pipelines for real-world time-series data.
• Rapidly iterate on approaches based on experimental results and product needs.
• Collaborate with hardware, sensing, and ML teams to integrate your work into training and evaluation pipelines.

Skills

Deep learning

Generative models

Time-series data

PyTorch

Ownership mindset

Education

MS or PhD in CS/EE/Applied Physics/ML or related field

Tools

COMSOL

Job description

We are looking for a Machine Learning Engineer in NYC with a background in generative modeling to help build the next generation of AI models for understanding human behavior. This role is ideal for someone who enjoys turning early technical ideas into robust AI systems and building a core technology platform from the ground up, using simulation and generative models to scale training far beyond what real-world data collection alone can achieve. You will work as part of the founding team across machine learning, sensing, data, software, and product. This is a full-time, on-site role in New York City.

The Focus

Develop generative models that improve how machine learning models are trained and evaluated on real-world sensing data.

What You Will Do

• Design, build, and validate simulation and generative modeling pipelines for real-world time-series data.
• Rapidly iterate on approaches based on experimental results and product needs.
• Collaborate with hardware, sensing, and ML teams to integrate your work into training and evaluation pipelines.

What We Are Looking For

• Strong foundation in deep learning, including experience with generative models and/or PINNs.
• Comfort working with real-world time-series data, noisy signals, ambiguous requirements, and fast iteration cycles.
• Experience with PyTorch or similar machine learning frameworks.
• Experience with multiphysics simulation (i.e., COMSOL) is strongly preferred.
• Ability to move quickly from prototype to working systems while maintaining engineering rigor.
• Ownership mindset, practical problem-solving ability, and comfort working in an early-stage startup.
• MS or PhD in Computer Science, Electrical Engineering, Applied Physics, Machine Learning, or a related field. Exceptional undergraduate candidates with strong relevant experience will also be considered.
• Publications in venues such as NeurIPS, ICML, ICLR, or related venues are a plus, but not required.

The Perks

Direct collaboration with the founding team, competitive pay, equity, top-tier VC backing, and a rare opportunity to help build a "Zero to One" technology company at the intersection of AI, wearables, and real-world human behavior understanding.

Salary Range: 160-200K base salary + equity

Location: In-person, New York City