Suggested rewrite: Led a cross-functional initiative that improved [business outcome] by [measurable result], demonstrating experience relevant to this role...
Backend Engineer- Inference Services
Review the role, location requirements, compensation details, and application process before deciding whether this opportunity fits your next career move.
- Remote from
- USA
- Salary
- USD 150k–220k / yr
- Department
- Software Engineering
- Employment
- Full Time
- Experience
- Senior
- Published
- Apply before
- 28 Nov 2026
- Listing views
- 27
- Application actions
- 3
Make your next move.
Prepare your resume, explore your fit, and draft a cover letter for this opportunity.
The role, at a glance.
Deepgram is hiring a Backend Engineer to build and improve inference services for speech-processing products. The role focuses on secure, scalable distributed services, networking, audio transcoding, compute orchestration, scheduling, and latency and memory optimization. Candidates need at least three years of industry experience, strong Rust, C, or C++ skills, Python proficiency, Git, and UNIX systems expertise. This is a high-impact, fast-moving engineering position that requires frequent experimentation with AI tools and close collaboration with Product. Experience with machine learning frameworks, transformer architectures, and audio processing is a strong advantage.
Role DNA
A quick view of the complexity, pace, ownership and collaboration implied by the job description.
Pace & Pressure
5/5Autonomy Level
4/5Communication Load
4/5Salary analysis
Estimated compensation compared with the broader US market for similar roles.
Core skills
Skills and capabilities most closely associated with this opportunity.
Sample interview questions
I would first validate the metric and segment it by model, endpoint, region, request size, and deployment version. I would correlate latency with CPU, GPU, memory, network, queue depth, scheduling, and downstream dependency metrics, then use tracing and profiling to isolate the slow path. After reproducing the issue where possible, I would mitigate the highest-impact bottleneck and add monitoring or regression tests to prevent recurrence.
I would separate request admission, scheduling, execution, and result delivery into clearly defined components with observable interfaces. The scheduler would account for resource availability, model affinity, queue priority, deadlines, and backpressure, while workers would be designed for safe retries and graceful failure handling. I would also build in capacity metrics, load shedding, and horizontal scaling so the system remains reliable under variable demand.
Key considerations include memory ownership and allocation behavior, concurrency safety, efficient serialization, connection management, and minimizing unnecessary copies. I would profile before optimizing, focus on the critical path, and use bounded queues and backpressure to avoid unbounded resource use. Strong testing, sanitizers, structured logging, and safe rollout practices are also essential for maintaining reliability in systems-level services.
I would establish quality and latency baselines, profile the pipeline, and identify costly decode, encode, conversion, and data-copy operations. Possible improvements include batching where latency budgets permit, using streaming processing, selecting efficient codecs or sample-rate conversion paths, and exploiting hardware acceleration when appropriate. Every change would be validated with representative audio, load tests, and quality metrics to ensure performance gains do not harm output quality.
I assess customer impact, reliability risk, time sensitivity, technical debt, and the likelihood that the problem will recur. For an urgent and well-understood issue, I prefer a narrowly scoped, observable fix with a rollback plan, followed by a documented plan for deeper improvements. If the existing design creates systemic risk or blocks future work, I align stakeholders on a staged redesign with milestones and measurable outcomes.
About this role.
Company Overview
Deepgram is the leading platform underpinning the emerging trillion-dollar Voice AI economy, providing real-time APIs for speech-to-text (STT), text-to-speech (TTS), and building production-grade voice agents at scale. More than 200,000 developers and 1,300+ organizations build voice offerings that are ‘Powered by Deepgram’, including Twilio, Cloudflare, Sierra, Decagon, Vapi, Daily, Cresta, Granola, and Jack in the Box. Deepgram’s voice-native foundation models are accessed through cloud APIs or as self-hosted and on-premises software, with unmatched accuracy, low latency, and cost efficiency. Backed by a recent Series C led by leading global investors and strategic partners, Deepgram has processed over 50,000 years of audio and transcribed more than 1 trillion words. There is no organization in the world that understands voice better than Deepgram.
Company Operating Rhythm
At Deepgram, we expect an AI-first mindset—AI use and comfort aren’t optional, they’re core to how we operate, innovate, and measure performance.
Every team member who works at Deepgram is expected to actively use and experiment with advanced AI tools, and even build your own into your everyday work. We measure how effectively AI is applied to deliver results, and consistent, creative use of the latest AI capabilities is key to success here. Candidates should be comfortable adopting new models and modes quickly, integrating AI into their workflows, and continuously pushing the boundaries of what these technologies can do.
Additionally, we move at the pace of AI. Change is rapid, and you can expect your day-to-day work to evolve just as quickly. This may not be the right role if you’re not excited to experiment, adapt, think on your feet, and learn constantly, or if you’re seeking something highly prescriptive with a traditional 9-to-5.
Opportunity:
Deepgram is looking for a Backend Software Engineer to join the Engine team to lead the design and implementation of Deepgram’s products. You will design and implement secure, robust, and scalable services for speech processing; efficient, distributed compute orchestration; optimized scheduling, and more. Your skill at building highly reusable code that overcomes technical challenges is paired with an intuition for delightful user experiences. You will be a critical voice in Deepgram’s Product and Engineering teams, driving high impact products from start to finish.
What You’ll Do
Improve Deepgram’s core inference services including areas in networking, speech processing, audio transcoding, and latency and memory optimization
Develop processes for measuring, building, and optimizing services to maximize system performance
Debug complex system issues that include networking, scheduling, and high performance computing interactions
Rapidly customize backend services to support our customer needs
Partner with Product to design and implement new services, features, and/or products end to end
You’ll Love This Role If You
Thrive in a fast-paced, impact-driven environment where learning new skills on-the-fly is not only encouraged but a regular necessity
Enjoy balancing decisions about product and feature maturity to decide when to make minimally invasive changes versus when to incorporate detailed design work
It’s Important To Us That You Have
3+ years of experience in an industry role
Programming experience in Rust (or C, C++), with competence in Python
Excellent communication and organizational skills, both written and verbal.
A high level of experience and understanding of version control; preferably git.
Comprehensive experience with UNIX-style systems.
It Would Be Great if You Had
Experience with modern machine learning, such as experience with a framework like Torch or implementation knowledge of architectures like CNNs, RNNS, and transformers
Experience with audio processing
Notice: We’re aware of individuals impersonating Deepgram recruiters. All legitimate Deepgram recruiting communication comes from an @deepgram.com email address. If you’ve received a message claiming to be Deepgram, please forward it to careers@deepgram.com.
This job listing has been manually reviewed by the Jobicy Trust & Safety Team for compliance with our posting guidelines, including verification of the company's legitimacy, accuracy of job details, clarity of remote work policy, and absence of misleading or fraudulent content.
Apply now.
Follow the employer’s application method and review Jobicy’s safety guidance before sharing personal information.
Continue on the employer website
Protect your personal information and never pay to secure an interview or job offer. .
