Serverless AI Inference - run any model, at any scale, without managing GPUs
AI Researcher – Inference Optimization
Location
Worldwide
Posted
134 days ago
Salary
0
Seniority
Senior
Job Description
AI Researcher – Inference Optimization
Featherless AI
• Research and develop techniques to optimize inference performance for large neural networks. • Improve latency, throughput, memory efficiency, and cost per inference. • Design and evaluate model-level optimizations (quantization, pruning, KV-cache optimization, architecture-aware simplifications). • Implement systems-level optimizations (dynamic batching, kernel fusion, multi-GPU inference, prefill vs decode optimization). • Benchmark inference workloads across hardware accelerators. • Collaborate with engineering teams to deploy optimized inference pipelines. • Translate research insights into production-ready improvements.
Job Requirements
- Strong background in machine learning, deep learning, or AI systems.
- Hands-on experience optimizing inference for large-scale models.
- Proficiency in Python and modern ML frameworks (e.g., PyTorch).
- Experience with inference tooling (e.g., Triton, TensorRT, vLLM, ONNX Runtime).
- Ability to design experiments and communicate results clearly.
Benefits
- Health insurance
- Flexible work arrangements
- Professional development opportunities
Related Guides
Related Job Pages
More AI Research Scientist Jobs
Applied AI Research Scientist, LLM
Confisa International GroupConnecting Top Brands with Top Talent Everyday
• Design graduate- and research-level evaluation questions grounded in hardware and computer engineering domains • Create tasks that require precise, step-by-step technical reasoning with verifiable ground-truth answers • Develop multimodal prompts when appropriate • Evaluate AI models on hardware- and systems-heavy reasoning tasks • Identify and document model failure modes • Provide authoritative solutions for each evaluation task • Maintain detailed records of prompts, expected answers, and outcomes
Principal AI Scientist
Cerence Inc.Cerence is the global industry leader in creating AI-powered user experiences for automotive and transportation.
• Architect, design, and implement state-of-the-art Generative AI models (auto-regressive, diffusion, Discrete Diffusion, Hybrid SSM etc ) and port these models to any hardware platform. • Leverage your expertise to effectively train, fine-tune, and optimize models that impact LLMs (Multimodal & Multilingual). • Collaborate closely with cross-functional teams comprising agentic AI scientists, software engineers, and domain experts. • Innovate and enhance existing applications by integrating the power of LLMs/MLLMs, thereby ensuring optimal performance and speed even on resource-constrained platforms. • Stay fully abreast of the latest advancements, trends, and research in the realms of Generative AI, Conversational AI, and language modeling.
General Specialist – AI Trainer
Invisible AgencyEmployment type: Freelance / Contract Workplace type: Remote Seniority level: Mid‑Senior Level
This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more. Role Description Are you eager to shape the future of AI? Large-scale language models are transforming the way we learn, work, and communicate—moving beyond simple tasks into tools that can support education, research, and professional practice across industries. With high-quality training data, tomorrow’s AI can become smarter, more reliable, and more useful for people everywhere. That training data begins with you. We’re looking for motivated individuals who are eager to contribute to the development of cutting-edge AI systems. You’ll work hands-on with advanced AI tools, test model outputs, evaluate responses for accuracy and clarity, and provide structured feedback to strengthen model performance. On a typical day, you will: - Engage with AI across a wide range of topics - Review its responses for quality - Document errors or gaps - Collaborate with our team to refine prompts, tasks, and evaluation methods Your ability to think critically, spot inconsistencies, and communicate feedback clearly will directly influence how well the model learns. Early-career professionals and recent graduates preferred. No prior AI or technical experience is necessary—just curiosity, strong communication skills, and a detail-oriented mindset. Experience in research, writing, tutoring, or problem-solving will be considered a plus. Ready to launch your career in AI by helping train the systems that will shape the future? Apply today and start turning your skills into impact. Qualifications - Curiosity and strong communication skills - Detail-oriented mindset - Experience in research, writing, tutoring, or problem-solving (considered a plus) - Early-career professionals and recent graduates preferred Requirements - No prior AI or technical experience necessary - Ability to think critically and spot inconsistencies - Ability to communicate feedback clearly Benefits - Pay range of $18 per hour - Exact rate determined after evaluating experience and geographic location - Final offer amounts may vary from the pay range listed - As a contractor, you’ll supply a secure computer and reliable internet connection - Company-sponsored benefits such as health insurance and PTO do not apply Company Description
Model Behavior Tutor - Social Cognition & EQ
xAIxAI’s mission is to create AI systems that can accurately understand the universe and aid humanity in its pursuit of knowledge. Our team is small, highly motivated, and focused on engineering excellence. This organization is for individuals who appreciate challenging themselves and thrive on curiosity. We operate with a flat organizational structure. All employees are expected to be hands-on and to contribute directly to the company’s mission. Leadership is given to those who show initiative and consistently deliver excellence. Work ethic and strong prioritization skills are important. All employees are expected to have strong communication skills. They should be able to concisely and accurately share knowledge with their teammates.
This description is a summary of our understanding of the job description. Click on 'Apply' button to find out more. Role Description You will make Grok extraordinarily adept at reading emotional subtext, social context, and user intent, then responding with perfect calibration. Responsibilities - Detect and interpret implied emotional states, attachment styles, and unspoken needs. - Teach models appropriate mirroring, boundary-setting, defusing, challenging, or comforting. - Detect and correct emotionally tone-deaf responses in AI-generated outputs. - Build datasets exposing dark-pattern social tactics (concern-trolling, gaslighting, etc.) so Grok remains immune. - Ensure cross-cultural sensitivity without performative overcorrection. Qualifications - Direct clinical experience with diverse populations (trauma, PTSD, personality disorders, neurodivergence, etc.). - Expertise in attachment theory, polyvagal theory, mentalization, or equivalent frameworks. - Demonstrated ability to read subtext and calibrate responses in high-stakes therapeutic or educational settings. - Familiarity with DSM-5 diagnostics and evidence-based interventions (CBT, DBT, trauma-focused modalities). - Strong ethical grounding and understanding of scope-of-practice boundaries. Preferred Qualifications - Active or past clinical licensure. - Experience supervising clinicians or teaching at the postgraduate level. - Published research or clinical writing on trauma, emotional regulation, or social cognition. - Public policy or advocacy experience around mental health. Location & Other Expectations - Tutor roles may be offered as full-time, part-time, or contractor positions, depending on role needs and candidate fit. - For contractor positions, hours will vary widely based on project scope and contractor availability, with no fixed commitments required. On average most projects may involve at least 10 hours per week to achieve deliverables effectively though this is not a fixed commitment and depends on the scope of work. - Contractors have full flexibility to set their own hours and determine the exact amount of time needed to complete deliverables. - Tutor roles may be performed remotely from any location worldwide, subject to legal eligibility, time-zone compatibility, and role specific needs. - For US based candidates, please note we are unable to hire in the states of Wyoming and Illinois at this time. - We are unable to provide visa sponsorship. - For those who will be working from a personal device, your computer must be a Chromebook, Mac with MacOS 11.0 or later, or Windows 10 or later. Compensation - US based candidates: $45/hour - $70/hour depending on factors including relevant experience, skills, education, geographic location, and qualifications. - International candidates: Information will be provided to you during the recruitment process. Benefits - Benefits vary based on employment type, location and jurisdiction. - Benefits for eligible U.S. based positions include health insurance, 401(k) plan, and paid sick leave. - Specific details and role specific information will be provided to you during the interview process.


