A deep learning engineer for teams that need one without a full-time hire. I take open-weight vision models from raw data to a production endpoint on infrastructure you control — then keep them running. Your data stays inside, and the weights stay yours.
Trusted by teams at
Every request ships your images and documents to someone else's servers, under someone else's terms.
Per-token pricing punishes you for using the product more. Self-hosted inference costs what the hardware costs.
You cannot fine-tune it, pin a version, or take it with you when the vendor changes the pricing.
The whole life cycle, or the part of it you are missing. Each one of these already shipped for someone — the work below is the proof.
The model that fits your data, not a generic one. Pretraining from your raw images when labels are scarce, finetuning open weights with LoRA and QLoRA when they exist, and the benchmark that says it beat what you had.
Shipped: Privhti EO satellite segmentation · DINOv3 multi-spectral · Qwen3-VL finetuning
See the training workThe model behind a URL your code can call. An OpenAI-compatible endpoint on your own hardware, vLLM picked automatically on NVIDIA GPUs, and streaming that keeps long video and heavy scenes inside a real memory budget.
Shipped: SursumAI · Tesla BEV Cam · cloudpurge · Digital Twinning
See SursumAIThe product around the endpoint. Ingestion, batching, storage and the application logic that turns a model call into something your users actually press a button for.
Shipped: KlipMind · client pipelines in production
See the pipelinesYour data, your hardware, your latency budget and what can never leave your network.
The right model picked and trained on your data, then measured against your baseline.
Live behind an endpoint you control, on your machines, with code and weights handed over.
Not an agency and not a hire: someone who works inside your stack for as long as you need deep learning done, and steps back when you don't. Three ways in.
A short, fixed start — before anyone commits to anything bigger.
You get
Your deep learning engineer and ML ops, by the month, part-time.
You get
One defined thing, taken from raw data to production and handed over.
You get
Most teams need deep learning in bursts: a model to get working, then months of it just running.
Teams that need a vision model working now, without building an ML department first.
Where the data cannot leave the building, and an external API is not an option.
Multi-spectral segmentation, cloud removal and land-cover analysis at scale.
Bird's-eye-view perception, real-time depth and reconstruction from video.
Your model. Your machine. Your URL. Deploy open-weight and custom models on your own hardware and get an OpenAI-compatible endpoint. No terminal, Docker, or GPU knowledge needed. Picks vLLM automatically on NVIDIA GPUs.
Visit sursumai.comStreaming pipeline that lets Depth Anything 3 run on long video sequences and large-scale scenes under tight CPU/GPU memory budgets, chunking frames and carrying state across chunks for stable online inference.
View on GitHubTwo 3D reconstruction pipelines compared on the same multi-view capture: SAM3 segmentation feeding COLMAP sparse and dense MVS, against 3D Gaussian Splatting converted to mesh with SuGaR. Both end in textured geometry.
View on GitHub
Stacks cloudy Planet imagery over clean Sentinel-2 of the same place. Detects the clouds, opens a hole through them and the surrounding haze, matches brightness by histogram, and composites with a feathered edge so the seam disappears.
View on GitHubBird's-eye-view perception system replicating Tesla FSD's surround-camera fusion pipeline for real-time vehicle and lane reconstruction.
View on GitHub
Multi-spectral semantic segmentation of satellite imagery for Earth Observation, built for Privhti EO's geospatial intelligence platform.
View on GitHubLocal video summarizer that runs entirely on-device. No data leaves your machine. Extracts key moments and generates structured summaries from any video file.
View on GitHub
Adapting DINOv3 self-supervised features to multi-spectral imagery for dense similarity mapping, enabling zero-shot land-cover analysis without labeled data.
View on GitHub
CLI for fine-tuning and fast inference of Qwen3-VL with LoRA/QLoRA, adapting open-weight vision-language models to domain data with minimal VRAM.
View on GitHub
Deep Learning Engineer | Pretraining, Finetuning, Inference & Serving Vision Models
Brasil · 4,590 followers
No. Smaller models run on CPU through llama-server. If you have an NVIDIA GPU, SursumAI picks vLLM automatically for far higher throughput.
No. Training and inference run on your machines. I work inside your environment and nothing is uploaded to a third party.
You do. Everything built in the engagement is handed over at the end, including training code, serving code and model weights.
If a closed API covers your case and the data is not sensitive, use it. Open weights win when data cannot leave, when usage is heavy enough that per-token pricing hurts, or when you need to fine-tune and own the model.
Vision and multimodal models: Qwen-VL, DINOv3, Depth Anything, SAM, Prithvi, YOLO, and whatever fits the problem.
Neither, usually. Most of the work is part-time and ongoing — I act as the deep learning engineer your team doesn't have on payroll, by the month. If you'd rather scope a single build and take it from there, that works too.
Book a 30 minute call. We go through your data, hardware and constraints, and I tell you whether open weights make sense for your case.
Have a model that should be in production by now?
