Research Engineer, AI Models

<p><strong><span data-contrast="auto">Research Engineer, Applied AI</span></strong><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<p><strong><span data-contrast="auto">Location:</span></strong><span data-contrast="auto"> Germany</span></p>
<p><strong><span data-contrast="auto">About EnCharge AI:</span></strong><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<p><span data-contrast="auto">EnCharge AI is building the next generation AI platform. Our novel in-memory-computing architecture delivers a 10x step-function improvement in compute energy efficiency and performance for AI inference workloads. As the demands of artificial intelligence move beyond today's models, we believe fundamental underlying infrastructure must evolve. We are an experienced team of AI researchers, silicon & systems engineers, and architects backed by leading investors, poised to become the essential platform for the next wave of AI innovation.</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<p><strong><span data-contrast="auto">The Opportunity:</span></strong><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<p><span data-contrast="auto">Modern AI workloads—from large language models to diffusion-based generators to multimodal systems—represent some of the most compute-intensive frontiers in AI, and some of the most promising applications for our hardware’s energy efficiency advantages. We’re building a vertically integrated AI stack that will showcase the transformative potential of our silicon while delivering real value to customers today.</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<p><span data-contrast="auto">We are seeking a Research Engineer to push the boundaries of AI model capability, quality, and efficiency. You’ll build fine-tuning and post training pipelines, develop rigorous benchmarking frameworks, and work at the intersection of ML research and hardware-aware optimization—ensuring our models run beautifully on our silicon.</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<p><span data-contrast="auto">This is a role for someone who thrives at the boundary between research and engineering. You’ll read papers, implement techniques, and ship production-quality code—all in service of making AI inference faster, cheaper, and better.</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<p><strong><span data-contrast="auto">Key Responsibilities:</span></strong><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="10" data-list-defn-props="{"335551671":2,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="2" data-aria-level="1"><strong><span data-contrast="auto">Algorithmic Acceleration:</span></strong><span data-contrast="auto"> Research and implement state-of-the-art techniques to accelerate AI inference—quantization, sparsity, distillation, speculative decoding, caching strategies, and architectural modifications. Systematically characterize tradeoffs between model quality, latency, throughput, and power consumption to find optimal operating points across different use cases. </span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="10" data-list-defn-props="{"335551671":2,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="3" data-aria-level="1"><strong><span data-contrast="auto">Hardware Co-Design:</span></strong><span data-contrast="auto"> Partner closely with hardware, compiler, and quantization teams to ensure algorithmic improvements translate to real gains on our silicon. Identify optimizations aligned with our architecture's strengths—maximizing throughput while minimizing power. Shape the feedback loop between model development and hardware.</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="10" data-list-defn-props="{"335551671":2,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="4" data-aria-level="1"><strong><span data-contrast="auto">Evaluation:</span></strong><span data-contrast="auto"> Build profiling tools and comprehensive benchmarking frameworks to understand compute bottlenecks, measure model quality across standard and domain-specific evals, and track efficiency metrics. </span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
<li data-leveltext="" data-font="Symbol" data-listid="10" data-list-defn-props="{"335551671":2,"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"hybridMultilevel"}" data-aria-posinset="5" data-aria-level="1"><strong><span data-contrast="auto">Applied Research:</span></strong><span data-contrast="auto"> Build robust fine-tuning workflows for modern AI models, enabling rapid experimentation with LoRA, adapters, and full fine-tuning. Stay current with the rapidly evolving landscape—evaluate new architectures, implement promising techniques, and contribute insights that inform technical and go-to-market strategy.</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<p><strong><span data-contrast="auto">Qualifications:</span></strong><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="1" data-aria-level="1"><span data-contrast="auto">5+ years of experience in ML research, applied ML, or ML systems</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="2" data-aria-level="1"><span data-contrast="auto">Strong fundamentals in Python and PyTorch</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="auto">Hands-on experience with transformers, diffusion models, state space models etc.</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="auto">Experience fine-tuning large models and building training/evaluation pipelines</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="auto">Deep understanding of transformers, attention mechanisms, & optimization techniques</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="12" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="6" data-aria-level="1"><span data-contrast="auto">Comfort reading and implementing techniques from research papers</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<p><strong><span data-contrast="auto">Nice to Have:</span></strong><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></p>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="1" data-aria-level="1"><span data-contrast="auto">Experience with efficient inference techniques (KV cache optimization, attention variants, MoE routing, flow matching)</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="2" data-aria-level="1"><span data-contrast="auto">Background in hardware-aware ML optimization or quantization</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="3" data-aria-level="1"><span data-contrast="auto">Familiarity with profiling tools (PyTorch Profiler, Nsight, custom instrumentation)</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="4" data-aria-level="1"><span data-contrast="auto">Publications in generative modeling, efficient inference, or ML systems</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<ul>
<li data-leveltext="" data-font="Symbol" data-listid="1" data-list-defn-props="{"335552541":1,"335559685":720,"335559991":360,"469769226":"Symbol","469769242":[8226],"469777803":"left","469777804":"","469777815":"multilevel"}" data-aria-posinset="5" data-aria-level="1"><span data-contrast="auto">Contributions to open-source ML projects</span><span data-ccp-props="{"134233117":true,"134233118":true,"201341983":0,"335559740":240}"> </span></li>
</ul>
<p class="p1">The salary range for this position is €116,000 to €154,000 EUR per year. Actual compensation offered will be determined based on job-related knowledge, skills, and experience.</p>