วิทยาศาสตร์ข้อมูล Jobs

JOB: Computational Biologist / ML Engineer - Brain-Specific Neoantigen Prediction Tool PROJECT OVERVIEW: I am building a brain-specific neoantigen prediction tool for mRNA/LNP/PNA therapeutics. The goal is to predict which mutated peptides (neoantigens) are most likely to be presented by HLA in brain metastasis and trigger an immune response. This is a 7-stage pipeline with a defined step list. WHAT YOU WILL BUILD: Stage 1 - Data Sourcing - Search and download brain metastasis MS immunopeptidomics data from CPTAC, SysteMHC, GEO, PRIDE - Download TCGA primary tumour WES/RNA-seq (20 samples) - Download BrainMetShare brain metastasis WES/RNA-seq (20 samples) - Download GTEx normal brain expression, AFND HLA frequencies, IEDB self-antigens - Record sample metadata (source, cancer type, ance...

NOTE: This is purely intellectual partnership. Money is not a motivation in this project. Seeking an established researcher for long-term collaboration in computational/structural biology. Applicants focusing solely on "Thesis Writing" or similar services will not be considered. Requirements: * PhD in CS, computational science, bioinformatics, statistics, or related field * Established publication record * Professional standing to serve as a future academic/industry referee Collaboration: * Strengthen methodology and experimental design * Perform supplementary analyses * Co-write manuscripts and reviewer responses * Provide a reference letter after an established collaboration Full co-authorship for contributions meeting authorship standards, with opportunities for follow-u...

Build real-time fraud scoring for Swift Tech Co.'s FinTech clients, models that have to catch fraud without declining a real customer's legitimate transaction. Responsibilities • Build and tune real-time transaction fraud-scoring models • Design rule-based fallback logic for cases a model shouldn't decide alone • Investigate false positives and tune thresholds against real transaction data • Work with compliance staff on FINTRAC-aligned reporting for confirmed fraud

I am looking for an experienced Python and Machine Learning developer to build an AI-based bias correction model for WRF 2-meter temperature (T2m) forecasts. Historical data will include WRF forecasts and observed temperatures from weather stations . The goal is to train a model to predict forecast bias and produce corrected temperature forecasts.

I am ready to commission a full-length, original research manuscript in artificial intelligence / machine learning that is suitable for submission to a Scopus-indexed, SCI-listed journal. At this stage I have no fixed problem statement, so I will rely on you to help shape a strong, publishable research question, design the methodology, run the experiments, and craft the paper end-to-end. Note : Apply only if you have a good publication record. Key deliverables • 2-3 complete manuscript (abstract through references) ready for journal submission • All code, datasets or preprocessing scripts required to reproduce the results • A concise response letter template explaining originality, significance and potential reviewer concerns Acceptance criteria will be clarity ...

I need help turning a sizable collection of unstructured finance-related text and document feeds into an accurate, production-ready predictive model. My goal is to spot patterns that reliably forecast the target variables I will share once we start (think risk scores and market-driven KPIs). The raw inputs arrive as news articles, earnings transcripts, and PDF reports, so the first step is a solid NLP-centric pipeline that cleans, tokenises, and extracts meaningful features. I work in a regulated environment, which means the code must be reproducible, well-commented, and easy to audit. Python with libraries such as spaCy, Hugging Face Transformers, pandas, and scikit-learn—or an equivalent stack—makes the most sense to me, but I’m open to a better suggestion as long as i...

I have a clean, ready-to-use Iris dataset and need a complete Support Vector Machine classification pipeline built around it. The job is straightforward: tune an SVM (scikit-learn or similar) to separate the three Iris species, document the process, and hand over reproducible code and results. Here’s what I expect: • A concise notebook or script that loads the data, performs any minimal preprocessing you find beneficial, runs hyper-parameter optimisation, trains the final model, and outputs accuracy, precision, recall and the confusion matrix. • A short write-up (markdown inside the notebook is fine) explaining why the chosen kernel and parameters work best, plus any insights you notice in the feature space. • Saved model file so I can deploy or reload it quickl...

The statistical groundwork is finished: 106,000+ football matches and more than 48 million individual odds movements are already structured, cleaned, and sitting in Python-ready data stores. What I need now is a fresh layer of intelligence that can group the patterns and pick up on the regime shifts as they occur —specifically, to surface the hidden structures that govern betting-market behaviour. This regime detection will challenge you immmensely but also matering it can provide enormous opportunity - are brave enough and smart enough to challenge the status quo?We have all the ground work laid and there is no statistical obvious deviation that favors the bet placer ONLY the BOOKIE over 106K of matches - and recent one months anlaysis - there is no ground work to be done only for y...

I'm seeking an expert to help with a research paper on AI/ML in healthcare to get published in IEEE conference as well as reputed journals Key requirements: - In-depth knowledge of AI/ML, especially in predictive analytics. - Experience with healthcare datasets, particularly patient medical records. - Strong research and writing skills. Ideal skills include: - Good research profile. - - Ability to present complex ideas clearly and concisely.

Post a table and a graph for: Real GDP and Nominal GDP together so you can visualize the difference and the trend. Describe the trend. For example: GDP increased all years, GDP grew more during the first n years and then dropped...? If there are important dips in GDP provide a possible reason. Real GDP Growth. Describe the trend. Did the economy experienced a recession? Which year(s)? Gini Coefficient. Describe the graph: income distribution got better/worse/same? provide a possible reason. Remember a lower GINI coefficient represents a better/ more equal income distribution. Nominal GNP and Nominal GDP. Compare GNP to GDP: is GNP larger/ smaller/ same as GDP? If different, why do have different values for the same country? National Income. Include all components (Wages, Interest, Rent, Pr...

I'm looking for a senior developer with hands-on experience defeating Arkose Labs FunCaptcha (specifically the newer game variants such as hopscotch_highsec / hopscotchv3) in a headless / API-based pipeline. ▎ ▎ I already have a working Node.js codebase that: ▎ - Mints Arkose tokens via a real-Chrome TLS client (bogdanfinn) ▎ - Rotates residential proxies + BDA fingerprints per attempt ▎ - Uses commercial classifiers (YesCaptcha, OmoCaptcha, ) ▎ ▎ The pipeline reaches the challenge-submit step consistently, but the classifiers we use are giving low-accuracy answers on the newer navigation-style variants, so we're getting solved:false on the final wave. ▎ ▎ What I need help with: ▎ - Diagnosing whether the failure is truly answer-quality vs a deeper trust/suppression issue ▎ - Imp...

Sessions will revolve around linear algebra, calculus, and probability as presented in the open-access text , always tying theory back to practical machine-learning use-cases. I am a Beginner and progress fastest through Kinesthetic (hands-on activities), so each concept should be paired with worked examples, code snippets in Python or MATLAB where relevant, and plenty of guided problem practice. What I need from you • Live, interactive lessons that unpack the core ideas behind vectors, matrices, multivariable calculus, limits, derivatives, integrals, random variables, and distributions, then connect them to algorithms such as gradient descent, PCA, and logistic regression. • Custom practice sets after every session, plus detailed walk-throughs of the solutions. • Bri...

Sessions will revolve around linear algebra, calculus, and probability as presented in the open-access text , always tying theory back to practical machine-learning use-cases. I am a Beginner and progress fastest through Kinesthetic (hands-on activities), so each concept should be paired with worked examples, code snippets in Python or MATLAB where relevant, and plenty of guided problem practice. What I need from you • Live, interactive lessons that unpack the core ideas behind vectors, matrices, multivariable calculus, limits, derivatives, integrals, random variables, and distributions, then connect them to algorithms such as gradient descent, PCA, and logistic regression. • Custom practice sets after every session, plus detailed walk-throughs of the solutions. • Bri...

I want to build an AI-driven module that sits alongside my existing trading setup and delivers continuous, real-time risk assessment for both the forex and cryptocurrency markets. The goal is simple: every open position and pending order should be evaluated second-by-second so I immediately see my true exposure and can take action before a drawdown spirals. Here’s what matters most to me: • Real-time risk assessment is the entire focus. Position sizing, margin usage, volatility spikes, correlation shifts, and news shocks all need to feed straight into the model so it can flag elevated risk instantly. • The first release only has to cover forex and crypto. If your architecture is flexible enough to extend into stocks later, that’s a plus but not required right now...

I need a fully-fledged, advanced-level course that dives deep into descriptive statistics and is ready for delivery as quickly as possible. The aim is to take learners who already know the basics and push them toward expert-level understanding of exploratory data analysis, high-dimensional summaries, and the latest visualization techniques. Here’s what I require: • Detailed syllabus that logically builds from core concepts (moments, shape, variability) toward multivariate and high-order descriptive measures. • Slide deck (PowerPoint, Keynote, or Google Slides) for each module, complete with speaker notes. • Practical notebooks or scripts in R or Python (your choice) that reproduce every example used in the slides. • At least two real-world datasets per mod...

I’m working through a graded assignment for my Data Science & AI course and need an expert hand with the assignment portion. The task isn’t massive, but it does require someone who can walk me through each step, provide clean, well-commented code (Python preferred), and explain the reasoning in plain language so I can confidently discuss the approach later. What I’ll need delivered: • A reproducible notebook or script that tackles the assignment requirements from data preprocessing through model evaluation • Brief inline comments plus a short write-up (one page is fine) summarizing methods, key metrics, and why those choices make sense • A quick call or chat after delivery so I can clarify any points before submission If that sounds straightforwa...

I am looking for an experienced agronomist to provide practical guidance throughout the growth and maintenance stages of my cereal crops. The main focus will be crop health, nutrient management, pest and disease monitoring, irrigation or moisture management, and maximising yield and grain quality. I will provide field history, soil-test results, crop information, and weekly scouting observations. I need these details translated into clear, practical recommendations that can be implemented in the field. The agronomist should be able to: * Analyse soil-test results and relate nutrient requirements to crop growth stages. * Recommend suitable fertiliser, micronutrient, and soil-amendment applications. * Identify potential nutrient deficiencies and crop stresses. * Establish practical pest, ...

My goal is to build an AI-driven inventory management application that keeps stock counts accurate to the second and helps me plan cash flow before problems arise. The core of the platform is real-time inventory tracking—every SKU, every location, synchronised automatically. Beyond the live view of stock, the system must: • run order management workflows end-to-end (receive, pick/pack/ship, confirm) • generate clear budget-forecast reports so I can see purchasing needs and working-capital requirements weeks ahead If predictive algorithms or machine-learning models improve the accuracy of those forecasts, please incorporate them. The finished software should be easy to use through a clean dashboard and expose a secure API for future integrations. Deliverables &b...

I’m sharing a rich, multi-sensor environmental dataset and I want to see just how much actionable knowledge you can squeeze out of it. Your mission is to surface at least 35 meaningful KPIs and supporting metrics, lay every calculation bare, explain why each one matters to real-world decision-making, and wrap it all into both an interactive Excel dashboard and an accompanying analytical report. The dataset blends multiple environmental streams, so correlations, anomalies, quality indicators, and uncovering hidden patterns are all on the table. I will reward depth of thought far more than flash: half of the score is tied directly to the strength, originality, and relevance of the KPIs you define. Methodology and transparent maths account for another 20 %, clarity of presentation 20 %...