Why Cast AI?

Cast AI is an automation platform that operates cloud-native and AI infrastructure at scale. By embedding autonomous decision-making directly into Kubernetes and cloud environments, Cast AI continuously optimizes performance, reliability, and efficiency in production.
The old way doesn't work. As Kubernetes and AI environments grow, manual decisions don’t. Cast AI replaces tickets, alerts, and manual tuning with continuous automation that adapts infrastructure as conditions change. Efficiency and cost savings follow naturally from that automation.
Over 2,100 companies already rely on Cast AI, including Akamai, BMW, Cisco, FICO, HuggingFace, NielsenIQ, Swisscom, and TGS.

Global team, diverse perspectives

We're headquartered in Miami, but our impact is international. We take a global and intentional approach to diversity. Today, Cast AI operates across 34 countries spanning Europe, North America, Latin America, and APAC, bringing a wide range of perspectives into how we build and lead.

Unicorn momentum

In January 2026, we achieved unicorn status with a strategic investment from Pacific Alliance Ventures, the corporate venture arm of Shinsegae Group (a $50+ billion Korean conglomerate). Our valuation now exceeds $1 billion, and we're just getting started.

Join us as we build the future of autonomous infrastructure.

About the role

Throughput. Latency. KV cache utilization.

Move those three numbers in the right direction, and two things happen: customers get faster, cheaper inference, and our margins improve. That's the entire thesis of this role. Every kernel you tune, every quantization scheme you ship, every scheduler tweak you land shows up directly in a customer's p99 and on our P&L.
This is a high-impact seat. It is also a high-autonomy seat as you'll be given the room to lead the technical direction of inference optimization at Kimchi, not execute someone else's roadmap.

The problem: running LLMs in production is a moving target. The "right" model and serving configuration for a workload depend on traffic shape, sequence-length distribution, batch dynamics, GPU SKU, memory bandwidth, quantization tolerance, and a dozen other variables that shift week to week. Most teams pick a model once, over-provision GPUs, and absorb the cost. Kimchi is the system that makes that decision automatically - continuously matching workloads to the most cost-efficient, best-performing LLM and serving configuration on a customer's infrastructure. We're building the optimization layer between the model and the hardware, and we need engineers who understand both sides deeply.

Stack

Python · vLLM · SGLang · TensorRT-LLM · PyTorch · CUDA-adjacent tooling · Kubernetes · gRPC · ClickHouse · PostgreSQL · GCP Pub/Sub · AWS / GCP / Azure · GitLab CI · ArgoCD · Prometheus · Grafana · Loki · Tempo.

Requirements:

• 5+ years building real ML systems, with a portfolio that shows depth in inference or training infrastructure (not just model training notebooks).
• Strong Python - production services, not scripts.
• Hands-on experience with at least one of vLLM, SGLang, or TensorRT-LLM, and a working mental model of why an inference engine performs the way it does on a given GPU.
• Fluency with quantization tradeoffs - you've measured quality regressions, not just compression ratios.
• Comfort with distributed systems: collective communication, sharding strategies, and the practical failure modes of multi-GPU and multi-node setups.
• A bias toward measurement. You instrument before you optimize, and you can tell the difference between a real win and a benchmark artifact.
• Self-direction. This role comes with a wide mandate; you should be excited by that, not unsettled by it.

Responsibilities:

• Push throughput. Continuous batching, speculative decoding, chunked prefill, kernel-level tuning across vLLM, SGLang, and TensorRT-LLM. Find the ceiling on each GPU SKU, then raise it.
• Cut latency. Attack TTFT and TPOT separately. Profile, identify the actual bottleneck (compute, memory bandwidth, scheduling, networking), and fix it - not the bottleneck you assumed.
• Get more out of the KV cache. Paged attention, prefix caching, eviction policies, cache reuse across requests, quantized KV. This is where a lot of the unrealized throughput lives, and it's an area you'll own.
• Quantize without regressing quality. INT8, INT4, FP8 across weights, activations, and KV. Empirical work: measure quality on real workloads, not just perplexity benchmarks.
• Shrink cold starts and memory footprint. Faster init, smarter weight loading, tighter memory accounting - the difference between a model that scales and one that doesn't.
• Scale across nodes. Distributed inference topologies, network-aware placement, checkpointing strategies that don't bottleneck on storage or interconnect.
• Set the technical direction. Decide what we benchmark, what we adopt, and what we build ourselves. Bring the team along with strong writeups and reproducible experiments.

What’s in it for you?

• Competitive salary (depending on the level of experience).
• Enjoy a flexible, remote-first global environment.
• Collaborate with a global team of cloud experts and innovators, passionate about pushing the boundaries of Kubernetes technology
• Equity options.
• Get quick feedback with a fast-paced workflow. Most feature projects are completed in 1 to 4 weeks.
• Spend 10% of your work time on personal projects or self-improvement. 
• Learning budget for professional and personal development - including access to international conferences and courses that elevate your skills.
• Annual hackathon to spark new ideas and strengthen team bonds.
• Team-building budget and company events to connect with your colleagues.
• Equipment budget to ensure you have everything you need.
• Extra days off to help maintain a healthy work-life balance.

Hiring process

• Screening call with Recruiter
• Hiring Manager interview
• Technical interview (system design)
• Live coding
• Culture Check interview with an executive

*As part of our standard hiring process, we would like to inform you that a background check may be conducted at the final stage of recruitment through our third-party provider, Checkr.
*Please note that Cast AI does not provide any form of visa sponsorship/work permit.

#LI-Remote

Job Title: Hardware Design Engineer

Reports to: Director of Hardware Engineering

Department: Engineering

💼 About the role

We’re seeking an experienced hardware design engineer to expand our cryptographic hardware IP team. You would be joining a mature design team with a proven track record of delivering market leading cryptographic IP, your role would expose you to the latest cryptographic standards and allow you to develop for the latest technologies.

We hope that you have at least 5 years of experience working on hardware design of complex IPs targeted at deployment on latest generation FPGAs, preferably with some experience working with cryptographic and security IPs.

 We have been established since 2018, so you would be directly working with the founders and inventors of this deep tech startup. The technology is already a couple of years in the making, its feasibility having been established, funding secured, and it has a clear path to market. This is a great opportunity for career progression and to get a head start in a rapidly expanding segment of the technology industry.

⚒️ What you’ll be doing

• Design and implementation of hardware IP blocks and subsystems.
• Tailoring implementations to FPGAs
• Working with verification engineers to create verification and test plans.
• Creation of reliable, reusable and excellently structured hardware design flows.
• Providing feedback to architects on feasibility of implementation and specification quality.
• Ensuring clean lint and implementation reports for IP blocks and subsystems.

🎯 Required Skills And Qualifications

• A commitment to high quality engineering in all areas of their work, including advocating for the best long-term solutions over the easiest or quickest.
• Optimising designs for both area and performance in FPGA technologies.  
• Experience building hardware IP blocks from scratch, and owning the process from initial specification through to customer delivery.
• Confidence bringing up a design using a basic “designers testbench”.
• Experience with standard commercial EDA Design tooling flows.
• Knowledge of common bus protocols (e.g. AMBA AXI4, AHB).
• Experience building and simulating hardware/software co-designs.
• Confidence in debugging RTL simulations issues.
• Degree or equivalent in Electronics/Computer Science or other related discipline.

🖥️ Specific Technologies You Are Confident Using

• FPGA and emulation experience. We use Xilinx FPGAs extensively for prototyping and hardware/firmware co-development.
• Logical IP design using SystemVerilog.
• Version control using Git.
• Writing System and subsystem level tests in C, using CMake as a build system.
• Confidence using tools like Bash, TCL, CMake and Makefiles safely and sensibly.

👍 Preferred Skills And Qualifications

• Python scripting for flows and automation 
• Experience debugging gate level simulations.
• Knowledge of Industry standard SoC Security Architectures
• Knowledge of tamper resistance and/or power side-channel security countermeasures.
• Experience using Gitlab CI, or otherwise principles of continuous integration and testing.

🏆 Some of the perks of working with us:

• Unparalleled opportunities to learn and accelerated career development.
• A collaborative, team environment with people who truly love what they do.
• Competitive salary and share option scheme.
• Flexible and hybrid working, and a working from home budget.
• Private health insurance for yourself and your family.
• 25 days annual leave (plus bank holidays and two wellness weeks).
• 50% gym membership discount.
• The chance to work with a spirited, smart, and friendly team!

Interested? Apply today to be part of the future of secure hardware! 🚀

Hardware Verification Engineer

Reports to: Lead Hardware Verification Engineer

Department: Engineering

Please note we can hire you in the following locations; UK, Germany, France, Belgium, Austria, Netherlands, Spain. 

If you are not based in one of these countries then we are unable to move forward with your application. 

💼 About the role

We’re seeking a Hardware Verification Engineer who thrives on solving hard problems, building tools that make life easier for others, and driving verification with both rigor and creativity. This is not a checkbox role — we want someone who is hands-on, curious, and motivated to go beyond the obvious.

The ideal candidate will have a strong background in software development, cryptography, and secure product development, with a focus on delivering secure, high-performance, and efficient products.

We have been established since 2018, so you would be directly working with the founders and inventors of this deep tech startup. The technology is already a couple of years in the making, its feasibility having been established, funding secured, and it has a clear path to market. This is a great opportunity for career progression and to get a head start in a rapidly expanding segment of the technology industry.

⚒️ What you’ll be doing

You'll be a part of a team verifying security-critical designs where thoroughness is everything. On a daily basis, you will:

• Build and extend UVM testbenches to verify cryptographic IPs and subsystems.
• Develop Python-based tools and automation to improve verification productivity.
• Use formal verification creatively, writing properties beyond canned apps to prove tricky scenarios.
• Debug at every level - from low-level waveforms to algorithmic mismatches.
• Collaborate with design, software, and architecture teams to ensure real-world use cases are covered.
• Approach designs with a "break it to make it" mindset, thinking like an attacher to expose weaknesses.

Key Job Functions

Beyond hands-on verification, you will also:

• Influence and define methodologies and strategies for design verification.
• Develop testbench architectures using UVM and formal-based approaches.
• Define verification plans, functional coverage models, and test strategies for block and subsystem verification.
• Lead verification at IP or SoC level, including effort estimation, scheduling, task assignment, and reporting progress to management.
• Drive coverage closure and sign-off quality across complex designs.
• Mentor junior engineers and help raise the team’s overall capability.

🎯 Required Skills And Qualifications

Preferred:

• Strong background in UVM-based verification at IP and subsystem levels.
• Proficiency in Python for tool development and automations.
• Practical formal verification experience, beyond app-based use.
• Knowledge of cryptographic algorithms (AES, SHA< ECC, etc.) and hardware/software security concepts.
• Software-oriented thinking (C/C++ or scripting languages) for HW/SW co-verification.
• Demonstrated leadership in planning and executing verification projects.
• Self-driven, resourceful, and persistent when solving tough technical challenges.
• Excellent debugging and problem solving skills with strong attention to detail.

🏆 Some of the perks of working with us:

• Unparalleled opportunities to learn and accelerated career development.
• A collaborative, team environment with people who truly love what they do.
• Competitive salary and share option scheme.
• Flexible and hybrid working, and a working from home budget.
• Private health insurance for yourself and your family.
• 25 days annual leave (plus bank holidays and two wellness weeks).
• 50% gym membership discount.
• The chance to work with a spirited, smart, and friendly team!

Interested? Apply today to be part of the future of secure hardware! 🚀

About the Role: 

As a Senior Software Engineer on the Calibration and Validation (CalVal) team, you will be a key contributor to the integrity and evolution of our geometric models. You will design and implement the automated, scalable processes required to ensure our products consistently exceed rigorous geometric specifications and SLAs. You will develop photogrammetric models, error budgets, and calibration concepts for our high-resolution and next-generation monitoring programs, ensuring spatial integrity across diverse fleets. Additionally, you will drive ongoing performance characterization and serve as a lead investigator for complex image quality issues—troubleshooting sensor models and geometric anomalies to architect the long-term fixes that maintain Planet's high standard of spatial data.

This is a full-time, remote position based in Austria. If located near an office, you are expected to work from that office 3 days per week.

Impact You’ll Own:

• Perform ongoing space imaging operations, geometric calibration activities and performance characterization
• Design and implement automated scalable processes to calibrate hundreds to satellites to ensure that our products meet and exceed specifications and SLAs
• Collaborate within a cross functional team to develop performance models, error budgets and calibration concepts for new very high resolution constellation
• Troubleshoot geometric image quality issues and developing long-term mitigations and fixes

What You Bring:

• 10+ years of industry experience with statistical processing and analysis techniques of large sets of measurement data
• Bachelor’s degree in Photogrammetry, Engineering, Physics, or Mathematics, relevant to geometric characterization of space imaging platforms
• Hands-on, can-do attitude, great interpersonal skills, and ability to collaborate effectively
• Understanding of end-to-end image processing chain – from sensor electronics and image ancillary data to geometric characterization
• Passion for Programming, Photography, Remote Sensing, Earth Sciences, and Geography
• Extensive experience leveraging scientific computing using Python in a Unix/Linux environment
• Knowledge of how to scale code with cloud computing resources, e.g. AWS or GCP
• Practical experience in solving problems by exploiting large cloud-based datasets

What Makes You Stand Out:

• 5+ years remote sensing experience + track record of software automation of analysis of imagery/maps
• Master’s degree or PhD in a relevant scientific/engineering field
• Hands-on experience with calibrating and operating very high resolution optical satellites
• Familiarity with design and construction of imaging/capture/camera hardware
• Active contribution to open source projects

Application Deadline:

June 11, 2026 by 11:59p / 23:59 CET (Central European Time)

Export Control Requirements:

Planet Labs Germany GmbH is authorized to receive U.S. export-controlled information at Planet under an export license issued by the Bureau of Industry and Security. This position requires access to export-controlled information, and as such, employment (or hiring of a contractor) is contingent upon the candidate’s ability to access all applicable export-controlled information without additional export licensing being required by the Bureau of Industry and Security and/or the Directorate of Defense Trade Controls.

Benefits While Working at Planet:

These offerings are dependent on employment type and geographical location, based upon applicable law or company policy.

• Paid time off including vacation, holidays and company-wide days off 
• Employee Wellness Program 
• Home Office Reimbursement
• Monthly Phone and Internet Reimbursement
• Tuition Reimbursement and access to LinkedIn Learning
• Equity 
• Volunteering Paid Time Off

#LI-REMOTE