---
title: 'Member of Technical Staff - Research, Inference at Modal'
canonical: 'https://feeny.ai/job/member-of-technical-staff-research-inference-modal-new-york-1a5bpnmmvvnx'
type: 'job'
last_seen: '2026-09-08'
---

# Member of Technical Staff - Research, Inference at Modal

- **Company:** Modal
- **Location:** New York, NY
- **Employment:** full-time
- **Posted:** 2026-07-05
- **Last confirmed live:** 2026-09-08
- **Apply:** https://jobs.ashbyhq.com/modal/73c97bbc-8e27-4c5d-b38b-90b3afdb0d93

## Job description

## ABOUT US:

AI needs a new infrastructure layer. We're building it at Modal.

Every era of computing brought new workloads that previous infrastructure couldn't support: mainframes, databases, and the cloud. Each time, the company that rebuilt the layer underneath defined the decade. AI is no different, except it touches everything instead of one slice, and the window to build the layer underneath it is open right now.

Our customers include category-defining companies like Lovable https://modal.com/blog/lovable-case-study, Ramp https://modal.com/blog/how-ramp-built-a-full-context-background-coding-agent-on-modal, Cognition, DoorDash, and Suno. They rely on Modal for instant GPU access, sub-second container starts, and native storage, so it's simple to serve low-latency inference, fine-tune models, and access production-ready sandboxes at scale.

We recently raised a $355M Series C https://modal.com/blog/modal-series-c at a $4.65B valuation, led by General Catalyst and Redpoint Ventures. We've crossed $300M+ ARR and grown fivefold since September.

Our team includes creators of popular open-source projects (e.g.,Seaborn https://github.com/mwaskom/seaborn,Luigi https://github.com/spotify/luigi), academic researchers, international olympiad medalists, and experienced engineering and product leaders with decades of experience.

## THE ROLE:

Most of the value of owning a model shows up at serving time. We're building a platform that covers the whole life of an LLM -- train it, deploy it, observe it -- and inference is where teams feel the difference every day. We already run elastic inference, sandboxes, distributed volumes, and multi-node training, and we control the infrastructure underneath, so the serving stack is ours to shape rather than something we resell.

You will do hands-on inference research at Modal, working with the research lead to pick high-impact bets and owning them end to end. The bets that matter most are the ones that move cost per token and tail latency on the workloads our customers actually run.

## WHAT YOU'LL DO:

- Own end-to-end inference research bets: speculative decoding, disaggregated prefill/decode, quantization (FP8, INT4), KV-cache and memory management, autoscaling for spiky serverless traffic, and whatever else the research agenda calls for.
- Train custom speculators against real production traffic and feed what you learn back into target models -- acceptance length is the metric that decides the win.
- Work directly with customers alongside our Forward Deployed Engineers to deploy and tune models, and bring what you learn back into the research.
- Carry and expand collaborations with outside research labs, for example:
- our work with ZLab on DFlash https://modal.com/blog/spec-is-all-u-need, a speculator design built on KV injection and blockwise parallel drafting
- our work with SGLang on specdec https://modal.com/blog/host-overhead-inference-efficiency and multimodal inference https://modal.com/blog/boosting-multimodal-inference-performance-by-greater-than-10-with-a-single-python-dictionary performance
- our work on Flash Attention 4 kernels https://modal.com/blog/flash-attention-4-faster
- Work with engineering to turn frontier serving techniques into products: primitives for disaggregation, fast weight refresh for models that keep training after deployment, observability for quality and latency in production, or even a next-generation inference engine.
- Help shape the research agenda. None of the above is prescriptive; your work will help guide our future.

## REQUIREMENTS:

- A research-leaning or systems background in LLM inference, with work you can point to.
- Fluency in the LLM serving stack, from kernels and quantization up to schedulers and autoscaling.
- A record of shipping research or systems that other people build on, whether in a lab or in industry.
- The drive to independently take a research bet from idea to result, working in the open with the rest of the team.
- Ability to work in-person, in our NYC or San Francisco office.

## About Modal

## Company Overview
- **One-liner**: Modal provides high-performance AI infrastructure—a serverless, globally distributed GPU cloud for inference, training, sandboxes, and agent workloads.
- **Entity Type**: Private (raised over $466M, Series D from top-tier investors)
- **Headquarters**: New York, NY, USA (with offices in Stockholm, Sweden and San Francisco, CA, USA)
- **Founded**: Not publicly available in provided sources
- **Founders**: Erik Bernhardsson and Akshat Bubna

## Core Business
- Primary industry: Cloud infrastructure / AI compute / Developer tools
- Target customers: Developers and engineering teams building AI/ML products (B2B, from startups to enterprises)
- Mission or purpose: “Make it easier to iterate and ship applications for data, AI, and machine learning” and “Make cloud development work like magic.”

## Products & Services
- **[Modal Runtime](https://modal.com/)** – Serverless container platform with custom file system, scheduler, and container image builder. Sub-second cold starts and instant autoscaling from 0 to 1000+ GPUs.
- **[Modal Sandboxes](https://modal.com/)** – Isolated, ephemeral environments for running untrusted code (e.g., coding agents, RL rollouts). Programmatically spin up fresh environments with custom images.
- **[Modal Inference](https://modal.com/)** – Globally distributed inference with sub-10ms overhead latency, support for token streaming, WebRTC, WebSocket. Supports LLMs, audio, image/video generation.
- **[Modal Training](https://modal.com/)** – Fine-tuning and multi-node training on H100s, A100s, B200s with gang scheduling and InfiniBand networking. Single line of code to scale from single-GPU to multi-node clusters.
- **[Modal Batch / Async Inference](https://modal.com/)** – Run evaluations, embeddings, re-ranking, dataset generation at scale, thousands of GPUs fully parallel.
- **[Modal SDK](https://modal.com/)** – Python SDK that lets developers define infrastructure and workloads in code, then ship to the cloud.

## Market Standing
- **Valuation**: $4.65B (as of 2026, per [jobsbyculture.com](https://jobsbyculture.com/blog/working-at-modal-2026))
- **Key Metric**: Total funding raised – over $466M (per [modal.com/company](https://modal.com/company))
- **Notable Investors/Partners**: General Catalyst, Redpoint Ventures, Lux Capital, Amplify Partners, Creandum (per [modal.com/company](https://modal.com/company))
- **Growth Signals**: ~150 employees (2026); global offices in New York, Stockholm, San Francisco; rapid hiring across engineering, GTM, and G&A roles; strong traction in inference, training, and agent infrastructure.

## Competitive Advantages
- **Deep infrastructure stack**: Custom file system, container runtime, scheduler, and image builder built from scratch to optimize AI workloads.
- **Developer experience**: “Stay in Python, ship to the cloud” – composable primitives that specify everything from logic to hardware in one code file.
- **Instant elasticity**: Scale from zero to 1000+ GPUs in seconds, pay only for compute used (no reserved capacity).
- **Global GPU access with low latency**: Sub-10ms overhead for online inference via globally distributed compute.
- **Compliance and security**: SOC 2 and HIPAA compliant, data residency controls, battle-tested isolation for untrusted code.

## Strategic Focus
- **AI-native runtime**: Deepening support for inference, fine-tuning, reinforcement learning, and agent workflows.
- **Scaling for agents**: Developing sandboxes and execution layers purpose‑built for interactive coding agents and long‑running RL rollouts.
- **Expanding global capacity**: Adding GPU availability across more regions, leveraging elastic cloud capacity.
- **Enterprise readiness**: Investing in security, governance, team controls, and data residency to serve larger customers.

## Why Work Here
- **Culture and team**: Founded by engineers who created open‑source tools (Seaborn, Luigi); team includes academic researchers, olympiad medalists, and experienced engineering leaders. Flat, high‑trust environment.
- **Location / flexibility**: Offices in New York, Stockholm, and San Francisco; likely hybrid/remote‑friendly (many roles list multiple locations).
- **Compensation and growth**: Transparent salary culture (as highlighted in 2026 profile); strong growth trajectory backed by $466M in funding and a $4.65B valuation.
- **Perks**: $30/month free compute for personal projects (customer benefit, likely similar for employees); focus on developer experience and “magic.”

## Sources
1. [modal.com](https://modal.com/)
2. [modal.com/company](https://modal.com/company)
3. [jobs.ashbyhq.com/modal](https://jobs.ashbyhq.com/modal)
4. [linkedin.com/company/modal-labs](https://www.linkedin.com/company/modal-labs)
5. [jobsbyculture.com/blog/working-at-modal-2026](https://jobsbyculture.com/blog/working-at-modal-2026)

## Other roles at Modal

- [Member of Design Staff - Brand](https://feeny.ai/job/member-of-design-staff-brand-modal-new-york-ccfxde25jatb) — New York, NY
- [Detection and Response Engineer](https://feeny.ai/job/detection-and-response-engineer-modal-new-york-93gcmptvvjtd) — New York, NY
- [Revenue Operations](https://feeny.ai/job/revenue-operations-modal-san-francisco-tpwq37mk240a) — San Francisco, CA
- [Regional Director](https://feeny.ai/job/regional-director-modal-new-york-ywxxargrqp0g) — New York, NY
- [ML Research Intern](https://feeny.ai/job/ml-research-intern-modal-new-york-67tppdwsng1t) — New York, NY
- [Member of Technical Staff - Research, Post-Training](https://feeny.ai/job/member-of-technical-staff-research-post-training-modal-new-york-zgntyn07gfp2) — New York, NY
- [People Operations Generalist](https://feeny.ai/job/people-operations-generalist-modal-new-york-bf7tqrws58xr) — New York, NY
- [Systems Engineering Manager](https://feeny.ai/job/systems-engineering-manager-modal-stockholm-c0pw8s1byfbj) — Stockholm, Sweden
- [Member of Technical Staff - Product (Growth)](https://feeny.ai/job/member-of-technical-staff-product-growth-modal-new-york-f2gm2kexkwpg) — New York, NY
- [Infrastructure Security Engineer](https://feeny.ai/job/infrastructure-security-engineer-modal-new-york-fjvfe2e55ns4) — New York, NY