Aurimas Griciūnas

Senior Solutions Architect

SwirlAI

Driving MLOps, Data Engineering and Machine Learning industry forward by helping professionals Level Up in these disciplines.

Founder & CEO

neptune.ai

Chief Product Officer

Head of Product

Driving MLOps industry forward by helping Neptune customers succeed in adopting MLOps best practices.

Transactie Monitoring Nederland (TMNL)

- Contributed to the development of end-to-end Machine Learning platform capabilities in a highly secure environment.
 - Focused on leveraging AWS SageMaker and supporting AWS services to enable scalable experimentation and model deployment.
 - Collaborated with the team to build reusable template libraries, streamlining the process of running ML experiments and deploying models efficiently and securely.

Senior MLOps Engineer

HomeToGo

- Led cross-functional teams of Cloud Engineers and Data Platform Engineers, driving key infrastructure and data initiatives.
 - Spearheaded a company-wide Cloud-Native Transformation initiative to modernize applications and infrastructure.
 - Championed the migration to Infrastructure as Code (IaC), standardizing infrastructure provisioning using Terraform for improved scalability, consistency, and automation.

Data Architect / Data Platform & Cloud Engineering Lead

- Led a Team of Data Engineers.
- Led a Team of Data Platform Engineers.
- Initiated and led a successful company wide Cloud Native Transformation.
- Migrated entire Data Platform Stack to Kubernetes. This included:

        - Airflow.
        - Superset.
        - Spark.
        - MLFlow.
        - Flink.
        - Airbyte.
        - DataHub.

- Introduced first Stream Processing applications that moved some of the Data Warehouse Processing stages upstream the pipeline.

Senior Data Engineer / Data Platform Team Lead

- Led a team of Data Engineers.
- Initiated and led a Data Warehouse migration from Redshift to Snowflake effort. It also included a refactoring of the Data Model.
- Oversaw Data migration from a Druid cluster to Redshift and later Snowflake.
- Introduced and rolled out Machine Learning Experiment Tracking System.
- Deployed and maintained first on-prem Kubernetes Clusters in the company.

Senior Data Engineer / Team Lead

- Led a successful implementation and optimisation of a custom Website Activity Tracking Ingestion Pipeline.
- Deployed and rolled out a company-wide Airflow Cluster.
- Led a full migration from Jenkins to Airflow for Data Engineering Pipelines.

Senior Data Engineer

Tesonet

Responsible for end-to-end development of ML-based products and big data solutions:

 - Identified business use cases suitable for machine learning and translated them into technical solutions.
 - Designed and implemented the full ML lifecycle, including data extraction, cleaning, validation, model training, packaging, and deployment.
 - Contributed to the architecture and development of scalable big data ingestion pipelines.
 - Set up and configured Kafka topics; developed real-time processing applications using Kafka Streams and Spark.

Senior Data Scientist/Engineer

Danske Bank

Projects I worked on:

-Affordability model enhancement using transaction data.
-Bringing transaction data into Balance Sheet stress-testing.
-Unlocking potential of transaction data throughout Risk Management function.
-Stress-testing of REA components and dynamic analysis on different credit portfolio levels.
-Process optimization and automation. Preparing models for production placement.

Senior Data Scientist/Analyst

Projects I worked on:

-Retail customer affordability project in Big Data analytics team.
-IFRS9 Life-time probability of default (LTPD) model development.
-IFRS9 Prepayment model development.
-IFRS9 impact on P&L analysis.
-IFRS9 and pre-IFRS9 ECL stress-testing and reporting.
-REA stress-testing and dynamic analysis on different credit portfolio levels.
-Process optimization by both improving old approaches and introducing new technologies.

Analyst

ADB Gjensidige

Was responsible for implementation of Solvency2 regulatory standards and providing required reports.

Actuary

Was responsible for generating business analysis reports for management.

Was responsible for calculation of Technical Reserves for Non-Life insurance products by applying different triangulation methods.

Junior Actuary

Follow me to learn about Data Engineering and ML Systems | Author of SwirlAI Newsletter | Public Speaker

Tired of all the noise surrounding AI space in recent years? Having a hard time keeping up with all of the news in the field and distinguishing what is really important? Follow me and subscribe to my newsletter to get actionable insights on building production ready AI Systems and keep track of only the important signal of what is happening in the AI world.

With over a decade of experience in Data Science, AI/ML Engineering, and MLOps, I’m also dedicated to helping practitioners level up their skills in MLOps, Data Engineering, Machine Learning, and related fields. I share my knowledge in a clear and accessible way to make learning straightforward and actionable.

If you want to partner with SwirlAI and get your product in front of 40K+ AI/ML/Data Engineers and Leaders via our Newsletter or 135K+ AI/ML/Data Engineers and Leaders via LinkedIn, contact me directly.

Leading Product Strategy.

TOON (Token-Oriented Object Notation) is out for some days now and it aims to make communication with LLMs more accurate and token-efficient.

The TOON topic is now one of the hottest news on the LLM market and it might actually matter.

𝗪𝗵𝘆 𝗜 𝘁𝗵𝗶𝗻𝗸 𝘀𝗼:

I was initially hesitant to cover this, potentially being another hype to quickly fade, but:

✅ The format has been shown to increase the accuracy of models while decreasing the token count. I was not sure if there were any accuracy retention studies made, it seems there were.
✅ Token efficiency is extremely important when working with Agentic Systems that require a lot of structured context inside of their reasoning chains. And we are moving towards a post-PoC world where there is a lot of emphasis placed on optimisation of the workflows.

𝗔 𝘀𝗵𝗼𝗿𝘁 𝘀𝘂𝗺𝗺𝗮𝗿𝘆:

- Token-efficient: typically 30-60% fewer tokens on large uniform arrays vs formatted JSON.
- LLM-friendly guardrails: explicit lengths and fields enable validation.
- Minimal syntax: removes redundant punctuation (braces, brackets, most quotes).
- Indentation-based structure: like YAML, uses whitespace instead of braces.
- Tabular arrays: declare keys once, stream data as rows.

An example:

𝘑𝘚𝘖𝘕 𝘧𝘰𝘳𝘮𝘢𝘵:

"shopping_cart": [
    { "id": "GDKVEG984", "name": "iPhone 15 Pro Max", "quantity": 2, "price": 1499.99, "category": "Electronics" },
    { "id": "GDKVEG985", "name": "Samsung Galaxy S24 Ultra", "quantity": 1, "price": 1299.99, "category": "Electronics" },
    { "id": "GDKVEG986", "name": "Apple Watch Series 9", "quantity": 1, "price": 199.99, "category": "Electronics" },
    { "id": "GDKVEG987", "name": "MacBook Pro 16-inch", "quantity": 1, "price": 2499.99, "category": "Electronics" }
  ]
}

𝘞𝘩𝘦𝘯 𝘦𝘯𝘤𝘰𝘥𝘦𝘥 𝘪𝘯𝘵𝘰 𝘛𝘖𝘖𝘕 𝘧𝘰𝘳𝘮𝘢𝘵:

shopping_cart: items[4]{id,name,quantity,price,category}:
    GDKVEG984,iPhone 15 Pro Max,2,1499.99,Electronics
    GDKVEG985,Samsung Galaxy S24 Ultra,1,1299.99,Electronics
    GDKVEG986,Apple Watch Series 9,1,199.99,Electronics
    GDKVEG987,MacBook Pro 16-inch,1,2499.99,Electronics

𝗥𝗲𝘀𝘂𝗹𝘁:

✅ 43% savings in token amount.
✅ Directly translates to 43% savings in token cost for this LLM input.

❗️ Be sure to know when NOT to use the format (and always test it for your application specifically):

- Deeply nested or non-uniform structures.
- Semi-uniform arrays.
- Pure tabular data.

ℹ️ I will be testing it in the upcoming weeks.

Let me know if you have already tested TOON and what are your takeaways! 👇

Founder @ SwirlAI • UpSkilling the Next Generation of AI Talent • Author of SwirlAI Newsletter • Public Speaker

𝗠𝗖𝗣 plus 𝗔𝟮𝗔, here is how they complement each other 👇

Protocol wars continue to rage, let's understand how Googles A2A (Agent2Agent) protocol is different from MCP and how they complement each other (read till the end).

𝘔𝘰𝘷𝘪𝘯𝘨 𝘱𝘪𝘦𝘤𝘦𝘴 𝘪𝘯 𝘔𝘊𝘗:

𝟭. MCP Host - Programs using LLMs at the core that want to access data through MCP.

❗️ When combined with A2A, an Agent becomes MCP Host.

𝟮. MCP Client - Clients that maintain 1:1 connections with servers.
𝟯. MCP Server - Lightweight programs that each expose specific capabilities through the standardised Model Context Protocol.
𝟰. Local Data Sources - Your computer’s files, databases, and services that MCP servers can securely access.
𝟱. Remote Data Sources - External systems available over the internet (e.g., through APIs) that MCP servers can connect to.

𝘌𝘯𝘵𝘦𝘳 𝘈2𝘈:

Where MCP falls short, A2A tries to help. In multi-Agent applications where state is not necessarily shared

𝟲. Agents (MCP Hosts) would implement and communicate via A2A protocol, that enables:

➡️ Secure Collaboration.
➡️ Task and State Management.
➡️ User Experience Negotiation.
➡️ Capability discovery - similar to MCP tools.

𝗛𝗼𝗻𝗲𝘀𝘁 𝘁𝗵𝗼𝘂𝗴𝗵𝘁𝘀:

❗️ Open protocols for Agent communication are important but they are just a piece of the picture, there will be a need for standards that govern all of the existing protocols and other missing pieces. E.g.

❓ How do we standardise tracing and Observability in multi-agent IOA systems?
❓ How do we retain the identity of the running job of an AI Agent instance if the communication standard is not unified in different parts of the pipeline?
❓ ... 

✅ More on this in my future posts, stay tuned!

Let me know your thoughts in the comments. 👇

Top-Tier Institution

Technology Specialist

Engineer

Global Financial Institution (Confidential)

Officer

Assistant Manager

GlobalLogic

Senior Software Engineer

HCL Technologies

Software Engineer

Follow for Your Daily Dose of AI, Software Development & System Design Tips | Exploring AI SaaS - Tinkering, Testing, Learning | Everything I write reflects my personal thoughts and has nothing to do with my employer. 👍

'Exploring AI SaaS - Tinkering, Testing, Learning'

As a technology enthusiast, I find immense joy in delving into new technologies and, more importantly, sharing the knowledge I gain with others every single day.

About Me:

🔸 A dynamic Team & Technical Lead, I thrive in collaborative environments, where I can lead and contribute as an individual to the team's success.

🔸 My expertise spans a wide array of projects, from web-based endeavors as a skilled Full Stack Developer to Java backend projects as a Backend Developer, and even complex Big Data initiatives as a proficient Data Engineer.

🔸 With an in-depth understanding of the end-to-end software development lifecycle, including Agile methodology and CI/CD practices, I consistently deliver efficient and scalable solutions.

🔸 Building distributed systems is my forte, leveraging cutting-edge technologies to create robust and scalable architectures.


Key Technical Strengths:

🔹 My proficiency in Data Structures & Algorithms forms the bedrock of my problem-solving abilities, enabling me to tackle complex challenges head-on.

🔹 I am well-versed in programming languages such as Java and Python, harnessing their power to craft elegant and efficient code.

🔹 My Big Data expertise includes mastery of Spark, Kafka, HDFS, Hive, HBase, and Flume, enabling me to process vast amounts of data with ease.

🔹 I excel in CI/CD practices, utilizing tools like Docker, Kubernetes, Red Hat Openshift, Jenkins, and GIT to ensure seamless and automated workflows.

🔹 I am well-versed in various frameworks, including Spring Boot for Microservices and Spring Batch, alongside my proficiency in Angular for crafting dynamic user interfaces.

🔹 My database prowess extends to MySQL, Oracle, and Cassandra, as well as HBase, ensuring optimal data storage and retrieval.

🔹 As a 5x Certified Microsoft Azure Engineer, I possess comprehensive cloud expertise, enabling me to architect and deploy scalable solutions.

I approach my work with boundless passion, consistently seeking to surpass expectations through continuous learning, exploration, and contributions that make a difference.

I look forward to connecting with like-minded individuals and exploring new opportunities to make a positive impact. 

Let's connect and explore exciting possibilities together! 🤝

Mayank A.

Build LLMs from Scratch 🚀

Found this gem by Vizuara, a 43-lecture series that actually delivers on its promise: building Large Language Models from the ground up.

What's inside:
→ Transformer architecture
→ GPT internals
→ Tokenization (BPE)
→ Attention mechanisms
→ Complete Python implementations

Perfect for ML engineers and developers who want to understand what's really happening under the hood of ChatGPT, Claude, and similar models.


🔗 [Playlist link in comments]

AG-UI is exploding and has crossed 150,000+ 𝐰𝐞𝐞𝐤𝐥𝐲 𝐝𝐨𝐰𝐧𝐥𝐨𝐚𝐝𝐬 (and climbing) and is one of the fastest-growing JavaScript AI package.

But it’s no surprise.

In a world where there’s a new agent framework every week, one thing has become clear:
𝐀𝐠𝐞𝐧𝐭𝐬 𝐚𝐫𝐞𝐧’𝐭 𝐩𝐫𝐨𝐝𝐮𝐜𝐭𝐬.
They need a real application layer where reasoning meets users.

That’s exactly why CopilotKit has quietly become the go-to stack for builders.
CopilotKit just crossed 25,000 𝐆𝐢𝐭𝐇𝐮𝐛 𝐬𝐭𝐚𝐫𝐬 🌟
And AG-UI is about to hit 10,000 𝐬𝐭𝐚𝐫𝐬 𝐧𝐞𝐱𝐭.
(If you haven’t starred it yet, now’s the time 👇)
⭐ https://lnkd.in/dn4Z64Gz

Why this matters:
We’ve trained agents to use tools (MCP)
We’ve let them talk to each other (A2A)
But we were missing the last piece…

How do agents talk to us? Live, interactively, inside any app?
The answer is 𝐀𝐆-𝐔𝐈, the Agent-User Interaction protocol.

It completes the trio:
𝐌𝐂𝐏 → agent ↔ tools
𝐀2𝐀 → agent ↔ agent
𝐀𝐆-𝐔𝐈 → agent ↔ user
This stack transforms disconnected “agent demos” into real, production-ready software.

And this is where CopilotKit comes in-
CopilotKit is the application layer where you can build Cursor-like AI experiences.

Out-of-the-box, you get:
Real-time shared state with your agent
UI components that stream reasoning + tool calls
Native support for A2A and MCP
A full framework to build “Cursor for [anything]”

If you want to build more than just an agent, like a real agentic application, CopilotKit is the place to start.

Let’s support one of the fastest-growing parts of the agent stack:
👉 Go star the AG-UI repo: https://lnkd.in/dn4Z64Gz ⭐

Mayank Ahuja

Infrastructure-as-code solved deployment. But it created a new problem: complexity at scale.

Hunting through AWS consoles to understand what's deployed. Manually tracking policy violations. Spending hours on Terraform migrations. Responding to CVEs one account at a time.

Generic AI promised to help. It failed because it doesn't understand YOUR infrastructure - just patterns from the internet.

Pulumi 𝐍𝐞𝐨 is different, and worth paying attention to.
Built on a context lake of your actual infrastructure - programs, state, policies, resource relationships.
It reasons from reality, not generic examples.

What this enables:
✅ Explain architectures conversationally
✅ Generate production-ready code from descriptions
✅ Migrate Terraform while preserving patterns
✅ Respond to CVEs across all accounts instantly
✅ Enforce policy compliance at organizational scale
...and 5 more workflows teams are running in production today.

The future of platform engineering isn't choosing between speed and safety. It's having both.

✔️ Get started for free => https://lnkd.in/dT79h-Uy
➕ Learn more about Pulumi Neo => https://lnkd.in/dSZJWCa2


----------
Their approach to grounded AI for infrastructure is genuinely innovative -  happy to collaborate with Pulumi to share these insights.

taplio

The Battle

Aurimas Griciūnas

Mayank A.

Followers

Posts

Engagements

Likes

Performance ScoreAurimas Griciūnas's LinkedIn Performance

Performance ScoreMayank A.'s LinkedIn Performance

Ready to grow your LinkedIn presence?

taplio

The Battle

Aurimas Griciūnas

Mayank A.

Followers

Posts

Engagements

Likes

Performance Score.css-goub6s{font-size:var(--chakra-fontSizes-md);font-weight:500;color:var(--chakra-colors-gray-600);display:block;margin-top:var(--chakra-space-1);}Aurimas Griciūnas's LinkedIn Performance

Performance ScoreMayank A.'s LinkedIn Performance

Ready to grow your LinkedIn presence?

Performance ScoreAurimas Griciūnas's LinkedIn Performance