ML Engineer – Test & Learn Platform

@sajjadtaghvaeifr

Hello, I trust you're doing well. I am well experienced in machine learning algorithms, with nearly a decade of hands-on practice. My expertise lies in developing various artificial intelligence algorithms, including the one you require, using Matlab, Python, and similar tools. I hold a doctorate from Tohoku University and have a number of publications in the same subject. My portfolio, which showcases my past work, is available for your review. Your project piqued my interest, and I would be delighted to be part of it. Let's connect to discuss in detail. Warm regards. please check my portfolio link: https://www.freelancer.com/u/sajjadtaghvaeifr

@vishal1145

Your experimentation platform will fail under production load if your Spark jobs aren't tuned for memory-efficient shuffles and partition skew. I've seen A/B testing pipelines crash during high-traffic experiments because the statistical engine couldn't handle 10M+ events per day without proper Delta Lake optimization. Before architecting the solution, I need clarity on two things: What's your current data volume per experiment (rows per day), and are you running multiple concurrent tests that require isolated compute resources? Also, does your causal inference layer need real-time results or can it tolerate batch processing delays? Here's the architectural approach: - PYSPARK + DELTA LAKE: Implement Z-ordering and data skipping on experiment_id columns to reduce query times from minutes to seconds when calculating treatment effects across 100M+ rows. - FASTAPI + CELERY: Build async endpoints that queue heavy statistical computations (DID, Synthetic Control) using Celery workers, preventing API timeouts during complex causal analysis. - DATABRICKS WORKFLOWS: Set up auto-scaling job clusters with dynamic partition pruning to handle variable experiment loads without over-provisioning resources. - DOCKER + KUBERNETES: Containerize the statistical engine with health checks and rolling deployments to ensure zero-downtime updates during active experiments. - PYTEST + CI/CD: Write property-based tests for hypothesis testing logic to catch edge cases like Simpson's Paradox before they corrupt experiment results. I've built 3 experimentation platforms that processed 50M daily events with sub-5-minute result latency. I don't take on projects where the statistical methodology isn't validated upfront. Let's schedule a technical call to discuss your variance reduction techniques and multiple testing correction strategy before implementation.

@KarthikTechCon

Hi, I’m Karthik, an ML/Data Engineering professional with 15+ years of experience building scalable analytics, cloud data pipelines, and ML-driven platforms across Azure and distributed environments. Your Test & Learn platform aligns well with my background in Python, PySpark, Databricks, FastAPI, and experimentation systems. I have hands-on experience developing statistical and ML workflows including A/B testing, hypothesis testing, and data-driven optimization pipelines. My expertise includes: • Python, Pandas, NumPy, Scikit-learn, SciPy • PySpark optimization, partitioning & OOM tuning • Databricks workflows & Delta Lake architecture • FastAPI service development • Azure Data Lake & cloud-native pipelines • Docker, Kubernetes & CI/CD automation • PyTest-based testing frameworks I’ve worked on large-scale data processing systems with Spark performance tuning, containerized deployments, and automated orchestration pipelines. I can collaborate closely with product and data science teams while ensuring production-grade reliability and scalability. Available to work remotely and travel to Bangalore when required. Regards, Karthik

@ashinnd84

Hello there, we are a team of senior Full Stack Web, Mobile App Developers and Designers. We can do this project in no time. Thanks Ashish Kumar.

@MuhammadAsad108

✔ I deliver 100% work — 99.9% is not for me. ✔ Workflow Diagram Requirement Analysis ⟶⟶ Causal Inference Modeling ⟶⟶ PySpark Pipeline Development ⟶⟶ FastAPI Service Integration ⟶⟶ Databricks Workflow Setup ⟶⟶ Docker & Kubernetes Deployment ⟶⟶ Testing & Performance Optimization ⟶⟶ CI/CD & Final Delivery Key Highlights ✔ Advanced ML experimentation systems — A/B testing, DID & Synthetic Control implementations. ✔ High-performance PySpark pipelines — optimized partitioning, memory handling & Spark tuning. ✔ Databricks expertise — Delta Lake workflows, orchestration & scalable processing. ✔ FastAPI backend services — secure, modular APIs for experimentation engines. ✔ Azure cloud integration — Data Lake, ML services & scalable deployment architecture. ✔ Production-ready DevOps — Dockerized services with Kubernetes deployment support. ✔ Strong testing standards — PyTest coverage, validation pipelines & CI/CD integration. ✔ Scalable statistical platform — designed for reliable data-driven decision-making. ✔ Clean, maintainable code — documented architecture with performance-focused implementation. Best Regards, Asad ML Engineer | PySpark & Databricks Expert | FastAPI & Cloud Architect

@sudhir0112

Hi! I'm Sudhir Jain — MIT graduate and ML Engineer with deep expertise in building and deploying ML systems at scale. As a former Google PM and data engineer at Axtria, I understand both the technical and product dimensions of ML platforms. For your Test & Learn Platform, I'll design and implement: - Experiment management framework (A/B testing, multi-armed bandits) - ML model versioning and automated retraining pipelines - Statistical significance testing and result interpretation - Real-time dashboards for experiment monitoring - Python-based ML pipeline with MLflow/DVC integration My background in predictive modeling, Python (Scikit-learn, TensorFlow, PyTorch), and business intelligence gives me a unique advantage. I deliver scalable, production-ready solutions. 100% completion rate. Let's discuss your requirements!

@dholadipak09

✨ Hi, I can help build and scale the Test & Learn platform with Python based statistical engines, FastAPI services, PySpark pipelines, and Databricks workflows. I have hands on experience with Python, Pandas, NumPy, Scikit learn, SciPy, FastAPI, PySpark, Docker, cloud data pipelines, and API backed analytics systems. For this role, I would focus first on building reliable experimentation modules for A/B testing, DID, hypothesis testing, and synthetic control, then expose them through clean APIs that can connect with product and data workflows. On the data side, I can work with Spark jobs, partitioning, memory tuning, Delta Lake style processing, and Databricks orchestration so the system remains stable as data volume grows. I can also add PyTest coverage, Docker setup, and CI/CD friendly structure so the platform is easier to maintain and deploy. I am comfortable collaborating remotely with data science and product teams, and I can manage the required Bangalore visits when needed. I would be happy to share my profile and discuss how I can contribute to your experimentation platform. Best regards Dipak ✨

@mussaibb7

I will design and deploy a scalable ML model on AWS to meet your project requirements, leveraging my expertise in building cloud-based ML systems, such as the Arabic Legal AI Retrieval System. With Python and AWS experience, I can quickly adapt to PySpark. What is the expected latency for the ML model inference and how will it be optimizedfor real-time performance in the cloud infrastructure? I specialize in fine-tuning and optimizing language models like GPT-4, which could be invaluable when working with your large-scale data pipelines and API development. Moreover, my experience with Databricks and Spark internals is well-suited to handle the memory, partitioning, and performance tuning challenges that often arise in ML engineering projects. I am also adept at using Docker and Kubernetes for containerizing and deploying applications - an essential aspect to ensure smooth integration. But while technical skill is crucial, I believe what truly sets me apart is my deep understanding of AI as a broader entity. I don't just build models; I design holistic systems that reason, act, and evolve, focusing on human-centered applications that create tangible value. Let's go beyond statistics and APIs—I want to help you make informed decisions using cutting-edge methods like causal inference.

@ahmadraza001912

I’ve worked on numerous projects involving the exact skillset you've listed in Spark, PySpark & Spark Internals, Databricks, and Causal Inference. Over the past 4+ years I have honed my expertise as a full-stack engineer with a speciality in Python. I am more than well-versed in Pandas, NumPy, Scikit-learn, and SciPy - enabling me to handle complex ML modeling tasks with ease. In terms of data pipelining, I have extensively used Azure Data Lake as well as PySpark and Delta Lake to design large-scale data processing workflows with industrial strength. With experience working on task management tools like Celery and Redis, plus knowledge of Polars, PyArrow, and SQLAlchemy – I'm well-equipped to optimize not only on the processing front but also databases & cloud storage. Containerization using Docker & Kubernetes has always been at the core of my development and deployment process. Moreover, I am adept at API Development having worked in junior-to-mid-level roles at prominent tech firms. Connectivity is key, that's why besides adaptation with FastAPI - Python's modern marvel - I'm also versed in RESTful & Web APIs. I understand your need for a remote contributor who can dive-in when needed - which is why I would be delighted to schedule those 1-2 visits required while primarily contributing from afar.

@praveent78

ML Engineer with FastAPI, PySpark pipelines, Docker, Kubernetes & ML deployment expertise. Interested! Alternative (more aligned to causal inference role): ML Engineer with FastAPI, data pipelines & statistical ML experience—ready to build scalable experiments. Stronger resume-focused version: Built scalable ML APIs, ETL pipelines & deployed AI systems on cloud—fit for this role.

@rahulsimraiya131

Hi, I can help build reliable experimentation and causal inference systems that turn raw data into clear, statistically sound decision-making tools. I’ve reviewed your requirements carefully, and the key challenge in these systems is balancing statistical accuracy with scalable engineering. Many experimentation platforms struggle because pipelines, APIs, and inference logic are not designed to work efficiently together at scale. What I’ll do for you: ◆ Build scalable experimentation and causal inference pipelines ◆ Develop APIs for model execution and result delivery ◆ Implement statistical engines for testing and analysis ◆ Optimize cloud-based workflows for performance and reliability ◆ Create clean, maintainable ML infrastructure for future scaling I focus on building systems that are not only technically correct but also production-ready, reproducible, and easy for teams to extend later. The goal is to help you make faster, data-backed decisions with confidence. Rahul

@Ashoksahu001

Dear Hiring Manager, I am excited to apply for the ML Engineer role. I have 7+ years of experience in Python development, backend systems, APIs, and cloud-based applications. My expertise includes Python, FastAPI, PySpark, Docker, Kubernetes, and scalable data processing solutions. I have experience building high-performance applications, optimizing workflows, and working with distributed systems and CI/CD pipelines. I am highly interested in experimentation platforms, causal inference systems, and data-driven product development. I would welcome the opportunity to contribute my technical skills and collaborate with your team. Best Regards, Ashok

@zain556

Hi there, I am writing to express my strong interest in your Test & Learn Platform project. With a deep background in Software Architecture and AI Automation, I specialize in building scalable, production-ready ML pipelines that don't just process data but drive actionable causal insights. How I Will Add Value: Statistical Engines: I have extensive experience implementing DID (Difference-in-Differences) and Synthetic Control models to move beyond simple correlation into true causal inference. Spark Optimization: I don't just write PySpark; I optimize it. I’m well-versed in handling OOM (Out of Memory) issues, data skews, and fine-tuning partitioning to ensure your Delta Lake operations are cost-effective and fast. Production-Grade APIs: Using FastAPI, I will build robust interfaces for your models, ensuring they are containerized via Docker/K8s for seamless Azure deployment. Reliable Pipelines: My workflow includes strict CI/CD integration (GitHub Actions/SonarCloud) and comprehensive PyTest coverage to ensure the platform stays stable as it scales. I am a founder of a digital solutions agency, so I bring a "systems-thinking" approach to your team, ensuring that the Databricks orchestration and Azure Data Lake architecture are perfectly synced. I am comfortable with the remote nature of the role and can easily manage the required visits to Bangalore. Let’s connect to discuss how I can help scale your experimentation engine.

@ayush020sahu2003

i know that this is a professional project and i am eager to do project like this since i am an fresher, i can work as per your modules without any hesitation just try me, i am a btech ai&ds grad so i can give you some hand on your project , but i do need some assistance to be honest from your side

@saddamh361

Hello there, I have experience working with Python ML systems, FastAPI services, PySpark pipelines, and cloud-based data workflows. I can help with: * A/B testing & causal inference models * FastAPI development * PySpark & Databricks optimisation * Azure data workflows * Docker/Kubernetes deployment Comfortable working on scalable ML experimentation platforms. Let's connect & discuss. Best Regards, Saddam H.

@krishd280

Hi, I’m interested in this ML Engineer opportunity. I have a strong interest in Python-based ML systems, FastAPI services, and scalable automation workflows. I’ve been actively working on AI/automation projects and continuously improving my backend and data engineering skills. I’m comfortable with Python, APIs, Docker-based environments, and debugging workflow issues. I’m also actively learning advanced ML pipeline concepts, distributed processing, and cloud-based architectures. Your focus on experimentation systems and scalable data workflows is especially interesting to me. I’m a fast learner, highly dedicated, and confident in adapting quickly to production workflows and collaborative environments. I’d love the opportunity to contribute and grow with your team.

@alluankit01

✨ Hi, I can support the Test and Learn platform as an ML Engineer focused on experimentation, causal inference, FastAPI services, and scalable PySpark pipelines. I have experience with Python, Pandas, NumPy, SciPy, Scikit learn, A/B testing, DID, hypothesis testing, FastAPI, PySpark, Delta Lake, Databricks workflows, Azure Data Lake, Docker, Kubernetes, PyTest, and performance tuning Spark jobs. My first focus would be to understand the current experimentation workflow, data volume, model requirements, and API contracts, then build clean statistical engines that are reliable for business decision making. For Spark work, I can handle partitioning, memory issues, OOM debugging, job optimization, Delta tables, and Databricks orchestration. I can also write tested APIs, containerize services, and keep the codebase ready for CI/CD and production deployment. I am comfortable with remote work, Bangalore visits if planned, and the ₹40,000 to ₹50,000 monthly range. Best regards Ankit ✨

@parask225

Hello, I’m a highly experienced ML Engineer specializing in experimentation platforms, causal inference, and large-scale data systems. I can help build a production-ready Test & Learn platform with optimized Spark pipelines, scalable APIs, and reliable statistical frameworks. My expertise includes: • Causal inference: A/B Testing, DID, hypothesis testing, experiment evaluation • Advanced PySpark optimization: OOM handling, partition tuning, caching, performance optimization • Databricks, Delta Lake, Azure Data Lake, workflow orchestration • FastAPI microservices and scalable backend architecture • Docker, Kubernetes, CI/CD, and PyTest-based testing • Python stack: Pandas, NumPy, SciPy, Scikit-learn I’ve built and optimized distributed analytics systems handling large-scale behavioral and transactional datasets, with focus on performance, scalability, and maintainability. I understand both the statistical and engineering side of experimentation systems, which helps bridge data science and production engineering effectively. What sets me apart: • Strong ownership from architecture to deployment • Production-focused, clean, scalable code • Fast debugging and optimization skills for Spark workloads • Clear communication and reliable delivery • Comfortable with remote collaboration and Bangalore visits I’m confident I can deliver a robust, scalable, and efficient experimentation platform aligned with your goals. Best regards.