---
title: 'Inference Performance Engineer at adaption'
canonical: 'https://feeny.ai/job/inference-performance-engineer-adaption-san-francisco-4zph5352xw0h'
type: 'job'
last_seen: '2026-09-12'
---

# Inference Performance Engineer at adaption

- **Company:** adaption
- **Location:** San Francisco, CA
- **Employment:** full-time
- **Work type:** hybrid
- **Posted:** 2026-08-21
- **Last confirmed live:** 2026-09-12
- **Apply:** https://jobs.ashbyhq.com/adaption/0be49174-9463-4c93-82d9-f227b0ab6a7c

## Job description

## The role

You'll own the cost and performance of our inference stack. Your work will determine how efficiently we serve models as workloads, traffic, and hardware change. You'll work closely with the engineers operating the serving fleet while owning the core performance levers: caching, batching, quantization, decoding, and kernel-level optimization. Success means improving throughput and latency without compromising reliability or model quality.

## Responsibilities

- Improve throughput, cost, and tail latency through KV-cache management, continuous batching, speculative decoding, and quantization.
- Optimize long-context prefill and decode workloads based on real production traffic.
- Tune routing between our infrastructure and external providers based on cost, capacity, and performance.
- Work within serving engines such as vLLM, SGLang, and TensorRT-LLM, going below the framework when needed.
- Build profiling and measurement systems that show where time, memory, and compute are being spent.

## Qualifications

- 5+ years in ML systems, inference infrastructure, or performance engineering, with measurable improvements in cost or latency.
- Deep understanding of model serving, including prefill and decode, memory bandwidth, batching, and concurrency.
- Production experience with serving engines such as vLLM, SGLang, or TensorRT-LLM.
- Strong Python skills and proficiency in C++, Rust, or another systems language.
- Experience with GPU performance, including CUDA, NCCL, mixed precision, memory layout, kernels, or quantization.

Above all, we're looking for great teammates who make work feel lighter and aren't afraid to go out on a limb with bold ideas. You don't need to be perfect, but you do need to be adaptable. We encourage you to apply, even if you don't check every box.

## About us

Most AI is frozen in place - it doesn't adapt to the world. We think that's backwards. Our mandate is to build efficient intelligence that evolves in real-time. Our vision is AI systems that are flexible, personalized, and accessible to everyone. We believe efficiency is what makes this possible - it's how we expand access and ensure innovation benefits the many, not the few. We believe in talent density: bringing together the best and most driven individuals to push the boundaries of continual adaptation. We're looking for builders and creative thinkers ready to shape the next era of intelligence.

## Benefits

- Flexible work: In-person collaboration in the Bay Area, a distributed global-first team, and team offsites.
- Adaption Passport: Annual travel stipend to explore a country you've never visited. We're building intelligence that evolves alongside you, so we encourage you to keep expanding your horizons.
- Lunch Stipend: Weekly meal allowance for take-out or grocery delivery.
- Well-Being: Comprehensive medical benefits and generous paid time off.

## About adaption

## Company Overview
- **One-liner**: Adaption builds adaptive AI systems that learn continuously and efficiently, moving beyond static models and expensive retraining cycles.
- **Entity Type**: Private (Seed Stage – $50M raised) [Fortune](https://fortune.com/2026/02/04/adaption-labs-50-million-seed-funding-emergence-captial-sara-hooker-sudip-roy-ai-models-that-learn-on-the-fly/)
- **Headquarters**: San Francisco, California, United States [LinkedIn](https://www.linkedin.com/company/adaption-labs)
- **Founded**: Not publicly available (founding team assembled around late 2025 / early 2026)
- **Founders**: Sara Hooker (former VP Research at Cohere) and Sudip Roy (former Director of Inference Computing at Cohere) [Fortune](https://fortune.com/2026/02/04/adaption-labs-50-million-seed-funding-emergence-captial-sara-hooker-sudip-roy-ai-models-that-learn-on-the-fly/)

## Core Business
- **Primary Industry**: Artificial Intelligence / Machine Learning
- **Target Customers**: B2B / Enterprise (hiring for Head of Enterprise Sales) [Careers](https://adaptionlabs.ai/careers)
- **Mission / Purpose**: Build extremely efficient AI that adapts in real time, treating constraints like latency, memory, cost, and energy as first-class design inputs so that intelligence evolves through interaction rather than brute-force scaling. [Website](https://adaptionlabs.ai/)

## Products & Services
- **[Adaptive Intelligence Platform]**: A system designed for continuous, on-the-fly learning without costly retraining or extensive prompt engineering. Combines adaptive data shaping, gradient-free learning, and co-designed hardware-algorithms to deliver highly efficient, domain-adaptable AI tailored to each task. [Website](https://adaptionlabs.ai/) – currently in waitlist phase.

## Market Standing
- **Valuation**: Not disclosed (company declined to provide) [Fortune](https://fortune.com/2026/02/04/adaption-labs-50-million-seed-funding-emergence-captial-sara-hooker-sudip-roy-ai-models-that-learn-on-the-fly/)
- **Key Metric**: $50M Seed Funding (led by Emergence Capital, with participation from Mozilla Ventures, Fifty Years, Threshold Ventures, Alpha Intelligence Capital, E14 Fund, and Neo) [Fortune](https://fortune.com/2026/02/04/adaption-labs-50-million-seed-funding-emergence-captial-sara-hooker-sudip-roy-ai-models-that-learn-on-the-fly/)
- **Notable Investors/Partners**: Emergence Capital (lead), Mozilla Ventures, Fifty Years, Threshold Ventures, Alpha Intelligence Capital, E14 Fund, Neo [Fortune](https://fortune.com/2026/02/04/adaption-labs-50-million-seed-funding-emergence-captial-sara-hooker-sudip-roy-ai-models-that-learn-on-the-fly/)
- **Growth Signals**: Headcount of 15 employees with +58.8% monthly growth; 23 active job postings; operates in 5 countries (US, Canada, India, Brazil, Peru); research team has 150+ publications across top AI conferences; backers include key players in AI and venture capital [LinkedIn](https://www.linkedin.com/company/adaption-labs)

## Competitive Advantages
- **Efficiency-first approach**: Unlike most labs chasing scale, Adaption prioritises low compute, low cost, and continuous adaptation – treating constraints as innovation drivers.
- **Real-time learning**: Enables models to update on-the-fly without retraining or fine-tuning, reducing enterprise overhead and latency.
- **World-class research talent**: Team brings deep expertise from Cohere, Google DeepMind, and Carnegie Mellon, with a track record of influential publications (including work on the “slow death of scaling”) [Research Page](https://www.adaptionlabs.ai/research)
- **Co-design of hardware and algorithms**: Systems are built from the ground up with serving constraints in mind, promising better efficiency at scale.

## Strategic Focus
- **Current Priority**: Move from waitlist to product-market fit, hiring across research, engineering, GTM, and design to build and deploy the first generation of adaptive AI for enterprise customers.
- **Direction for Growth**: Expand the platform to multiple industries and specialisations while continuing research into adaptive compute, on-the-fly alignment, and dynamic learning strategies. [Research Page](https://www.adaptionlabs.ai/research)

## Why Work Here
- **Culture**: Emphasises efficiency, real-world interaction, and product excellence as core design values. The team is small (~15 people), offering high impact and ownership from day one.
- **Work Model**: Hybrid, remote, and onsite options available across locations including San Francisco, New York, Toronto, London, and Singapore [Careers](https://adaptionlabs.ai/careers)
- **Roles**: Open positions in research (Research Scientist, Applied ML Engineer), engineering (Distributed Systems, Inference Platform), GTM (Growth Lead, Head of Enterprise Sales), and design (Product Designer). Contracts and full-time available.
- **Notable Perks**: Work with world-class AI researchers, access to strong funding runway, and the chance to define an entirely new approach to AI that challenges the dominant scaling paradigm.

## Sources
1. [Fortune](https://fortune.com/2026/02/04/adaption-labs-50-million-seed-funding-emergence-captial-sara-hooker-sudip-roy-ai-models-that-learn-on-the-fly/)
2. [LinkedIn](https://www.linkedin.com/company/adaption-labs)
3. [Website](https://adaptionlabs.ai/)
4. [Careers](https://adaptionlabs.ai/careers)
5. [Research Page](https://www.adaptionlabs.ai/research)

## Other roles at adaption

- [Agent Systems Engineer](https://feeny.ai/job/agent-systems-engineer-adaption-san-francisco-h8cqnbdpdary) — San Francisco, CA
- [Platform Engineer, APIs and Security](https://feeny.ai/job/platform-engineer-apis-and-security-adaption-san-francisco-m5790sxrdh93) — San Francisco, CA
- [Founding GTM Lead (North America)](https://feeny.ai/job/founding-gtm-lead-north-america-adaption-united-states-hckjtb0982gr) — United States
- [Modelling Resident](https://feeny.ai/job/modelling-resident-adaption-united-kingdom-dvtjh2en67mp) — United Kingdom
- [Senior Research Scientist](https://feeny.ai/job/senior-research-scientist-adaption-united-states-7zjjgvcywxmc) — United States
- [Research Scientist / Research Engineer](https://feeny.ai/job/research-scientist-research-engineer-adaption-united-states-gmjs4gbd3y7b) — United States