Member of Technical Staff, Image Generation

1 Month ago • All levels • Software Development & Engineering • $175,000 PA - $275,000 PA

Job Summary

Job Description

Captions is seeking an exceptional Member of Technical Staff to advance the state-of-the-art in large-scale image generation models. You will conduct novel research on generative image models for people and storytelling, developing new training techniques and scaling models to billions of parameters and millions of users. As a key member of our AI team, you will work at the cutting edge of image generation systems that enable natural, expressive, and high-fidelity outputs. The team has strong expertise in training large-scale models with demonstrated research and product impact, focusing on using image synthesis for multimodal video generation with an emphasis on photorealistic quality, professional-grade expressivity, and creative iteration.
Must have:
  • Design and implement large-scale image generation models.
  • Develop new approaches to multimodal conditioning.
  • Research advanced image-editing and generation techniques.
  • Establish and validate scaling laws for image diffusion models.
  • Develop automated evaluation approaches.
  • Drive rapid experimentation with model architectures.
  • Validate research through product deployment.
  • Derive insights from data and recommend architectures.
  • Train and optimize models at massive scale.
  • Push the boundaries of efficiency and hardware utilization.
  • Develop sophisticated distributed training approaches.
  • Design and implement model-compression techniques.
  • Create new approaches to memory optimization.
  • Research techniques for improving sampling speed.
  • Conduct systematic empirical studies.
Good to have:
  • Master’s or PhD in Computer Science, Machine Learning, or related field.
  • Experience implementing and improving state-of-the-art generative image models.
  • Deep expertise in generative modeling approaches.
  • Strong background in optimization techniques.
  • Experience with empirical scaling studies.
  • Track record of research contributions at top ML conferences.
  • Strong proficiency in modern deep-learning tooling.
  • Experience training image diffusion models.
  • Familiarity with large language models or multimodal transformers.
  • Deep understanding of attention, transformers, latent representations.
  • Expertise in distributed training systems.
  • Proven ability to implement complex model architectures.
  • Ability to write clean, modular research code.
  • Strong software-engineering practices.
  • Experience with rapid prototyping.
  • Strong analytical skills for debugging.
  • Familiarity with profiling and optimization tools.
Perks:
  • Comprehensive medical, dental, and vision plans
  • 401K with employer match
  • Commuter Benefits
  • Catered lunch multiple days per week
  • Dinner stipend every night if working late
  • Doordash DashPass subscription
  • Health & Wellness Perks (Talkspace, Kindbody, One Medical subscription, HealthAdvocate, Teladoc)
  • Multiple team offsites per year
  • Team events every month
  • Generous PTO policy

Job Details

Captions is the leading AI video company—our mission is to empower anyone, anywhere to tell their stories through video. Over 10 million creators and businesses have used Captions to simplify video creation with truly novel and groundbreaking AI capabilities.

We are a rapidly growing team of ambitious, experienced, and devoted engineers, researchers, designers, marketers, and operators based in NYC. As an early member of our team, you’ll have an opportunity to have an outsized impact on our products and our company's culture.

Our Technology

Mirage Announcement our proprietary omni-modal foundation model

Seeing Voices (technical paper) generating A-roll video from audio with Mirage

Mirage Studio for generating expressive videos at scale

"Captions: For Talking Videos” available in the iOS app store

Press Coverage

Lenny’s Podcast: Interview with Gaurav Misra (CEO)

Latest Fundraise: Series C Announcement

The Information: 50 Most Promising Startups

Fast Company: Next Big Things in Tech

Business Insider: 34 most promising AI startups

TIME: The Best Inventions of 2024

Our Investors

We’re very fortunate to have some the best investors and entrepreneurs backing us, including Index Ventures, Kleiner Perkins, Sequoia Capital, Andreessen Horowitz, Uncommon Projects, Kevin Systrom, Mike Krieger, Lenny Rachitsky, Antoine Martin, Julie Zhuo, Ben Rubin, Jaren Glover, SVAngel, 20VC, Ludlow Ventures, Chapter One, and more.

** Please note that all of our roles will require you to be in-person at our NYC HQ (located in Union Square)

We do not work with third-party recruiting agencies, please do not contact us**

About the Role

Captions is seeking an exceptional Member of Technical Staff to advance the state‑of‑the‑art in large‑scale image generation models. You’ll conduct novel research on generative image models for people and storytelling, developing new training techniques and scaling models to billions of parameters and millions of users. As a key member of our AI team, you’ll work at the cutting edge of image generation systems that enable natural, expressive, and high‑fidelity outputs.

Our team has strong expertise in training large‑scale models with demonstrated research and product impact (see our recent whitepaper here for details of recent work). We’re especially excited to push the use of image synthesis for multimodal video generation, with a focus on photorealistic quality, professional-grade expressivity, and creative iteration. Our models power tools used by millions of creators, and we’re tackling fundamental challenges in how to generate compelling composition, lighting, and fine‑grained detail across diverse domains.

Key Responsibilities

Research & Architecture Development

  • Design and implement large‑scale image generation models (transformers, latent diffusion, flow matching, etc.).

  • Develop new approaches to multimodal conditioning and generation (e.g. audio and video) and controllability (editing, multi-frame consistency, script guidance, etc).

  • Research advanced image‑editing and -generation techniques such as content‑preserving edits, multi‑input conditioning, and reference‑based generation.

  • Establish and validate scaling laws for image diffusion models across resolution and parameter count.

  • Develop automated evaluation approaches for improved fidelity and consistency.

  • Drive rapid experimentation with model architectures, sampling strategies, and training strategies.

  • Validate research directly through product deployment and real user feedback.

  • Derive insights from data and recommend architectures and training practices that will make meaningful impacts on our products.

Model Training & Optimization

  • Train and optimize models at massive scale (10s–100s of billions of parameters) across multi‑node GPU clusters.

  • Push the boundaries of efficiency and hardware utilization for training and deploying models in a cost effective manner.

  • Develop sophisticated distributed training approaches using FSDP, DeepSpeed, Megatron‑LM, Triton and custom CUDA kernels where needed.

  • Design and implement model‑compression techniques (pruning, distillation, quantization, etc.) for efficient serving.

  • Create new approaches to memory optimization, gradient checkpointing, and mixed‑precision training.

  • Research techniques for improving sampling speed (DDIM, PFGM++, SDE‑VE) and training stability at scale.

  • Conduct systematic empirical studies to benchmark architecture and optimization choices.

Preferred Qualifications

Research Experience

  • Master’s or PhD in Computer Science, Machine Learning, or a related field or equivalent practical experience.

  • Demonstrated experience implementing and improving state‑of‑the‑art generative image models.

  • Deep expertise in generative modeling approaches (flow matching / diffusion, autoregressive models, VAEs, GANs, etc.).

  • Strong background in optimization techniques, sampling, and loss‑function design.

  • Experience with empirical scaling studies and systematic architecture research.

  • Track record of research contributions at top ML conferences (NeurIPS, CVPR, ICCV, ICML, ICLR).

Technical Expertise

  • Strong proficiency in modern deep‑learning tooling (PyTorch, CUDA, Triton, FSDP, etc.).

  • Experience training image diffusion models with billions of parameters.

  • Familiarity with large language models or multimodal transformers is a plus.

  • Deep understanding of attention, transformers, latent representations, and modern image‑text alignment techniques.

  • Expertise in distributed training systems, model parallelism, and high‑throughput inference.

  • Proven ability to implement and improve complex model architectures end to end.

Engineering Capabilities

  • Ability to write clean, modular research code that scales from prototype to production.

  • Strong software‑engineering practices including testing, code review, and CI/CD.

  • Experience with rapid prototyping and experimental design under tight iteration loops.

  • Strong analytical skills for debugging model behavior, numerical stability, and performance bottlenecks.

  • Familiarity with profiling and optimization tools (Nsight, TensorBoard, PyTorch Profiler, etc.).

  • Track record of bringing research ideas to production and maintaining high code quality in a research environment.

About the Team

You’ll work directly alongside our research and engineering teams in our NYC office. We’ve intentionally built a culture where technical innovation and research excellence are highly valued. Your success will be measured by your contributions to improving our models and advancing the field, not by your ability to navigate politics. We’re a team that loves diving deep into complex technical problems and emerging with practical breakthroughs.

Our Team Values

  • Open technical discussions and collaboration

  • Rapid iteration and practical solutions

  • Deep technical expertise and continuous learning

  • Direct impact on research and product outcomes

What Sets Us Apart

  • Opportunity to advance the state‑of‑the‑art in multimodal video generation

  • Direct impact on products used by millions of creators

  • Access to massive compute resources and diverse, large‑scale datasets

  • Environment that values both research excellence and practical impact

  • Ability to validate research through direct product feedback

Benefits:

  • Comprehensive medical, dental, and vision plans

  • 401K with employer match

  • Commuter Benefits

  • Catered lunch multiple days per week

  • Dinner stipend every night if you're working late and want a bite!

  • Doordash DashPass subscription

  • Health & Wellness Perks (Talkspace, Kindbody, One Medical subscription, HealthAdvocate, Teladoc)

  • Multiple team offsites per year with team events every month

  • Generous PTO policy

Captions provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.

Please note benefits apply to full time employees only.

Similar Jobs

Riot Games - Staff Software Engineer - Infrastructure Reliability

Riot Games

Los Angeles, California, United States (On-Site)
3 Months ago
CAE - Hardware Engineer

CAE

Little Rock, Arkansas, United States (On-Site)
3 Weeks ago
Paytm - Akamai Engineer

Paytm

Noida, Uttar Pradesh, India (On-Site)
4 Months ago
WebMD - Senior Software Engineer

WebMD

Newark, New Jersey, United States (On-Site)
1 Month ago
Roblox - Senior / Principal Inference Engineer - ML Platform

Roblox

San Mateo, California, United States (On-Site)
1 Month ago
Minted - Engineering Manager, Shopping Data

Minted

(Remote)
2 Months ago
Lulalend - Senior Software Engineer

Lulalend

Cape Town, Western Cape, South Africa (Remote)
9 Months ago
Canva - Engineering Manager (BE) - Content Management & Distribution

Canva

Brisbane, Queensland, Australia (Remote)
3 Months ago
Shield AI - Staff Engineer, Integration and Software

Shield AI

San Diego, California, United States (On-Site)
1 Week ago
PwC - SAP CPI Professional Associate

PwC

Makati City, Metro Manila, Philippines (On-Site)
9 Months ago

Get notifed when new similar jobs are uploaded

Similar Skill Jobs

The Walt Disney Company - Senior Systems Engineer

The Walt Disney Company

New York, New York, United States (On-Site)
3 Months ago
Siemens  - Commvault Backup Architect

Siemens

Bengaluru, Karnataka, India (On-Site)
1 Week ago
Bazaar Voice - Senior Sales Operations Analyst - Tools Admin

Bazaar Voice

Bengaluru, Karnataka, India (Hybrid)
4 Months ago
Saronic Technologies - Mission Support Manager

Saronic Technologies

San Diego, California, United States (On-Site)
1 Week ago
Alpha Sense - Senior Engineer, iOS

Alpha Sense

Helsinki, Uusimaa, Finland (Hybrid)
2 Months ago
Synechron - Axiom Developer

Synechron

Plano, Texas, United States (On-Site)
2 Weeks ago
Rockstar Games - Animation Systems Programmer

Rockstar Games

Carlsbad, California, United States (On-Site)
2 Months ago
Ubisoft - Technical Director - Level Design

Ubisoft

Bordeaux, Nouvelle-Aquitaine, France (On-Site)
4 Months ago
CD PROJEKT RED - AI & Navigation Engineer

CD PROJEKT RED

Warsaw, Masovian Voivodeship, Poland (On-Site)
6 Months ago
Wind River - Technical Leader - DO178 V&V

Wind River

Bengaluru, Karnataka, India (Hybrid)
3 Months ago

Get notifed when new similar jobs are uploaded

Jobs in New York, New York, United States

Apple - Software Quality Engineer - Applied Networking

Apple

Cupertino, California, United States (On-Site)
3 Weeks ago
Next Level Business Services - SGV/AGV/ASRS Architect

Next Level Business Services

Philadelphia, Pennsylvania, United States (On-Site)
9 Months ago
Vercel - Data Analyst, Finance

Vercel

San Francisco, California, United States (Hybrid)
1 Month ago
QuinStreet - Senior Applied Machine Learning Engineer

QuinStreet

United States (Remote)
3 Months ago
Apple - SRE Engineer (Site Reliability Engineer)

Apple

Austin, Texas, United States (On-Site)
2 Months ago
Alten Technology - Business Manager

Alten Technology

Troy, Michigan, United States (On-Site)
2 Weeks ago
Bazaar Voice - Field Marketing Specialist

Bazaar Voice

Austin, Texas, United States (Hybrid)
3 Weeks ago
CyberArk - Strategic Partner Manager

CyberArk

United States (On-Site)
2 Months ago
Interactive Brokers - Senior Software Development Engineer in Test

Interactive Brokers

Greenwich, Connecticut, United States (Hybrid)
2 Months ago
Sika Group - Overnight Production Supervisor

Sika Group

Canton, Massachusetts, United States (On-Site)
3 Weeks ago

Get notifed when new similar jobs are uploaded

Software Development & Engineering Jobs

Tesla - Associate Technical Support Engineer (French Speaker)

Tesla

North Holland, Netherlands (On-Site)
5 Months ago
Sonar Source - Engineering Manager

Sonar Source

Geneva, Geneva, Switzerland (On-Site)
1 Year ago
Apple - Engineering Program Manager, AirPods Firmware

Apple

Cupertino, California, United States (On-Site)
4 Weeks ago
cyara - Senior Software Engineer

cyara

Hyderabad, Telangana, India (Hybrid)
1 Week ago
Maverick Games - Senior Engine Engineer

Maverick Games

Warwick, England, United Kingdom (Hybrid)
3 Months ago
Ion - Storage Engineer, Italy

Ion

Italy (Hybrid)
9 Months ago
Aptive - Software Engineer

Aptive

Bengaluru, Karnataka, India (On-Site)
1 Week ago
Accenture - Application Support Engineer

Accenture

Bengaluru, Karnataka, India (On-Site)
2 Months ago
Apple - Senior Software Engineer—Location Intelligence

Apple

Cupertino, California, United States (On-Site)
1 Month ago
Highspot - Senior Software Development Engineer

Highspot

Seattle, Washington, United States (Hybrid)
2 Months ago

Get notifed when new similar jobs are uploaded

About The Company

Captions is the leading video AI company, building the future of video creation. Over 10 million creators and businesses have used Captions to create videos for social media, marketing, sales, and more. We're on a mission to serve the next billion. We are a rapidly growing team of ambitious, experienced, and devoted engineers, researchers, designers, marketers, and operators based in NYC. You'll join an early team and have an outsized impact on the product and the company's culture.

New York, New York, United States (On-Site)

New York, New York, United States (On-Site)

New York, New York, United States (On-Site)

New York, United States (On-Site)

New York, United States (On-Site)

New York, New York, United States (On-Site)

New York, New York, United States (On-Site)

New York, United States (On-Site)

New York, United States (On-Site)

View All Jobs

Get notified when new jobs are added by Captions

Level Up Your Career in Game Development!

Transform Your Passion into Profession with Our Comprehensive Courses for Aspiring Game Developers.

Job Common Plug