Antonino Grasso
Software Engineer & Technical Lead · From Discovery to Production · M.Sc. Computer Science
- Munich, Germany
- antonino.grasso.it@gmail.com
- GitHub
Summary
Software engineer and technical lead. I take complex, vague problems from discovery to production systems, and set the technical direction for the team that builds them. Now technical lead of KUKA's global AI use case team: the technical counterpart when business units bring AI needs, owning architecture and use-case decisions, and taking the first, an AI sales-intelligence system I designed in pre-sales, from board-presented PoC toward production. Five years at Device Insight (KUKA Group), the first three alongside a dual degree, across backend, cloud infrastructure and, lately, AI systems; before that, built core features of an enterprise engineering-collaboration platform that served 10+ tenants. Alongside, I co-founded Bissig & Grasso, a small software and AI studio. M.Sc. Computer Science, grade 1.2.
Experience
Co-Founder — Bissig & Grasso GbR
Two-person software and AI studio, run alongside my full-time role.
- Help small companies save time with automation and AI tools
- Co-building Cauzar, a next-tier, AI-first observability platform on OpenTelemetry: the place engineers and their coding agents go to debug a system and spot the faint signal before anyone asks (beta)
- Building kaibo, a reviewed engineering doctrine that coding agents consult before acting (early release, used internally)
Device Insight GmbH (KUKA Group)
Technical Lead, Global KUKA AI Use Case Team
- Lead a five-person engineering team that builds the AI systems KUKA's businesses can't build in self-service: engineers own their use cases, and I guide the architecture and decisions across all of them
- Technical counterpart when business units bring AI needs: first calls, solution designs, PoCs and estimates, from sales intelligence to RFQ analysis and competitive intelligence
- Still hands-on: building the sales-intelligence system toward production as the team's first use case, scaling it from the 78-account PoC to KUKA's ~15,000 accounts
- Setting the team's engineering standards for building with AI (architecture decisions, review flow, verification gates)
Technical Lead, AI Sales Intelligence
Board-sponsored, built for KUKA's global sales organization
- Took the project from my own pre-sales solution design to a working PoC in ~2 months with a four-person team, on schedule, and presented it to KUKA's board and executive management
- Built an AI account-research pipeline (Kotlin, Anthropic API, web research) that turns hours of manual research into a ranked, explainable assessment in ~7 minutes at ~$1 per account
Co-Lead, Competence Center AI
- Co-lead Device Insight's Competence Center AI and drive its AI Systems track, shaping how the company approaches AI-system projects
- Built and own an agentic AI booking-check automation on Azure (Python) that flags mis-booked time in Harvest; in active use by PMs and productive with minimal maintenance, it has recovered ~€12k of revenue on ~$92 of run cost (~€134 back per $1)
R&D Software Engineer, Physical AI Midlayer
For KUKA's CTO Office: intent-based robotics R&D, embedded AI, multi-agent orchestration.
- Lead R&D engineer for the agentic-orchestration layer of an intent-based robotics platform: scoped open CTO-Office briefs, built the prototypes, and drove the architecture proposals and platform-evolution decisions, coordinating with stakeholders across related focus topics
- Built a working multi-agent orchestration prototype in Python, running on NVIDIA Jetson: evaluated LangGraph and Microsoft Agent Framework hands-on, picked direction, prototyped on-device inference (vLLM, quantization, with measurable token-throughput gains) designed to run offline / fully on-robot, plus error-tolerant task execution
- Built ROS2-MCP interop between the robotics stack and the agentic orchestration layer; validated it end-to-end on real hardware by wiring a five-finger robotic hand's gesture actions through ROS2 up to MCP
- Authored an 80-page internal whitepaper that drove platform-evolution decisions: selected which components advance to next-stage research, which architectural directions the platform takes
Software Engineer, Mosaixx
Cloud-native SaaS: collaborative engineering platform on AWS, shipped to 10+ enterprise tenants.
- Designed and shipped the token-based licensing system end-to-end: product requirements, database schemas and Flyway migrations, observability instrumentation, and dev/stage/prod rollout. Went live with 10+ enterprise tenants.
- Built the add-on management feature (S3 upload, association, lifecycle state changes, deletion) and integrated cloud-based software licensing
- Owned platform-wide observability: instrumented backend services with OpenTelemetry, set up tracing and metrics, built the local observability stack used across both dev teams
- Worked across backend, AWS infrastructure (AppStream, ECS), and DevOps: generalist scope on a 3–5 engineer team, one of two delivery teams in a ~20-person product org
- Collaborated closely with PMs, POs, and Go-to-Market on prioritization and product direction; represented the product at Automatica 2025 with live customer demos
Software Engineer (Dual Study Programme)
Alternating university semesters with full-time engineering rotations across IoT projects.
- Designed an AWS Cognito-based auth/authz system for an IoT product line, shipped during the dual-study period and still running in production today
- Designed and set up the Domain-API end-to-end testing framework for a wind-energy client, defining the testing strategy spanning domain API down through simulated devices to the data source
- Rotated across HVAC, access control, and green-energy IoT projects, building early breadth across production distributed systems, end-to-end lifecycle exposure (architecture → engineering → operations), and fast onboarding into unfamiliar contexts
Education
M.Sc. Computer Science (Software Engineering) — Hochschule München
- Final grade: 1.2
- Thesis: Navigating the Space Between Serverful and Serverless: Benefits, Drawbacks, Challenges and Mitigations
- Dual study (ICS model) @ Device Insight GmbH
- Student Tutor (undergraduate computer science coursework), Mar 2024 – Jul 2024
B.Sc. Computer Science — Hochschule München
- Final grade: 1.4
- Thesis: Construction of a Software Solution for Detection of End-of-Support Dependencies
- Dual study (ICS model) @ Device Insight GmbH
Technical Skills
I pick tools for the problem at hand, not out of habit. I've carried systems from first commit to production on several stacks, so I get productive fast on a new one.
- Build
- Kotlin, Python, Java, Go, TypeScript, Spring Boot, Ktor, FastAPI, REST / OpenAPI
- AI Systems
- Anthropic API, LLM evals, MCP, LangGraph, Microsoft Agent Framework, vLLM
- Agentic Engineering
- Claude Code, Paseo, Agent harness design (own tools: kaibo, turnstile, ADS)
- Ship
- AWS (ECS, Lambda), Azure (Container Apps), Kubernetes, Docker, Terraform, GitLab CI/CD, Azure DevOps
- Run
- PostgreSQL, Flyway, OpenTelemetry, Grafana