Open roles across every project and research thread.
Harden and extend the offline assistant — improve how reliably small on-device models handle assessment, tutoring, and content generation, and validate the outputs against curriculum standards and real classroom needs. Good if you like making agent systems actually hold up on constrained hardware.
4 contributors · 2 open
Build the part of the system that enforces hard safety rules and keeps its decisions traceable. Good if you like LLM agents and building things that fail safe.
4 contributors · 3 open
Build and improve the full grading pipeline end to end — agent logic, document ingestion, RAG retrieval, and rubric-aligned generation. Measure quality with benchmarking and ablation studies, with a path to co-authoring on a live institutional AI deployment. Good if you want to go deep on a system that runs in real university courses.
team of 4 · 1 open
Extend the multi-agent retrieval pipeline — improve specialist routing, retrieval quality, and LLM-scored ranking. Work directly on a live system used for clinical evidence search. Good if you want to go deep on agentic RAG beyond toy examples.
team of 1 · 3 open
Extend and improve the multi-agent pipeline — refine taste vector matching, add specialist agents (dietary, cuisine-specific), and improve group preference aggregation. Good if you want to go deep on multi-agent systems and personalization with real users.
team of 3 · 2 open
Evaluate retrieval quality across clinical domains, build benchmark datasets, and run ablation studies on retrieval and ranking strategies. The project has an active research thread — path to co-authorship. Good if you like measuring whether a system actually works and care about evidence quality in healthcare.
team of 1 · 3 open
Train the models that decide what gets recommended — retrieval, ranking, and sequential modeling. Every change is measured against a real offline eval harness (Recall@K, NDCG) before it ships. Good if you want to build recsys the way large-scale systems are built — not just cosine similarity.
team of 4 · 4 open
CCI framework architecture, methodology coordination, and paper positioning.
4 contributors · 2 open
Build per-book glossaries and validate translation quality across historical and low-resource languages, including old-print quirks, and curate ground-truth pages. Good if you care about doing justice to the source text.
3 contributors · 2 open
Own the learning-study design (within-subject, pre/post, IRB) and instantiate the method in a second, non-clinical domain to prove transfer across disciplines. Good if you care about learning that is measured, not assumed.
3 contributors · 2 open
Lead primary field research for Deployment Vertical 2. Document deployment environment ecosystem, economic baselines, supply chain dependency structure, and regional market access constraints.
1 contributors · 3 open
Build the data and delivery layer behind the product: a Postgres schema for users, flavor profiles, menus, and a persisted safety-gate audit trail, with the full test suite and eval benchmarks gating every merge.
team of 4 · 4 open
Build and maintain the product end to end: the FastAPI backend, SSE streaming layer, and AWS infrastructure, plus the clinician-facing search interface — real-time SSE evidence streaming, source highlighting, and quality indicators. Keep a live clinical tool fast, reliable, and observable.
team of 1 · 3 open
Build the product end to end — FastAPI backend, WebSocket group chat, social graph (friends, groups, collections), AWS Cognito auth, and the React discovery feed UI. This is a social product so both sides matter: fast APIs and a UX that makes group dining decisions fast and clear.
team of 3 · 2 open
Help build and maintain the AnacodicAI Labs website — the site you're looking at right now.
Owns the first-author writing and synthesis — turn the section drafts into one coherent argument, own the figures and the framing. Good if you want a lead-author byline on an invited review.
3 contributors · 2 open
Leads research direction, platform architecture, and cross-vertical deployment design.
1 contributors · 3 open
Leads benchmarking design, measurement framework, and experimental execution.
4 contributors · 2 open
Build the benchmark that shows how close the offline system gets to expensive cloud models — quality across the three tasks, plus the cost, latency, and memory of running on low-cost edge hardware. Good if you like building the arena that makes a result credible.
4 contributors · 2 open
Build the multi-region benchmark and the baseline suite the method must beat. Good if you like building the arena that makes a result credible.
5 contributors · 2 open
Build the matching and the longitudinal evaluation that proves the approach helps over months — not just a one-shot recommendation — while the primary goal stays protected.
1 contributors · 2 open
Build the measurement and analysis that shows whether learners' judgment actually improves over time — the study's statistics, reliability checks, and the comparison that tests whether the design helps rather than hurts. This is the result that makes the paper.
3 contributors · 2 open
Build the tests that prove the system is safe, not just accurate — design the evaluation and run the comparisons.
4 contributors · 3 open
Build the system that generates the picture panels and automatically checks each one is faithful to the single intended step before it ships — so the method scales without a human illustrator. Good if you like making generation reliable, not just pretty.
3 contributors · 3 open
Build the part that checks how consistent a questioned work is with an artist's confirmed self-portraits, and the calibrated confidence layer that can say 'not enough evidence' instead of guessing. Good if you like metric learning and honest probabilities.
2 contributors · 2 open
Build the vision pipeline that turns paintings into color and visual features, and the analysis and statistical test that check whether the changes across a career line up with real events better than chance. Good if you like turning pixels into defensible results.
3 contributors · 2 open
Help gather the real-world data that shows where SafeBite holds up and where it falls short — running small pilots with the right campus programs (we'll connect you) and bringing structured feedback back to the team. Good if you like turning messy real-world use into signal people can build on.
team of 4 · 4 open
Account for the energy, cost, and carbon of the system per query, and quantify its cost-versus-benefit tradeoff. Good if you care about the carbon of the intelligence, not just its accuracy.
5 contributors · 2 open
Support platform build and evaluation instrumentation. Implement agent coordination layer and deployment measurement framework.
1 contributors · 3 open
Assemble the Van Gogh and Munch painting corpus from museum open data and curate the timeline of life events the study draws on. Good if you like building clean, well-sourced datasets.
3 contributors · 2 open
Build the lesson-progression engine (one new element per step, concrete before abstract, mastery plus spaced repetition) and the evaluation protocol with non-reader participants. Good if you care about learning that is measured, not assumed.
3 contributors · 3 open
Build the pipeline that turns a scanned page into clean, structured text with a per-page confidence score, and the benchmark that scores recognition error, translation quality, and cost per accurate page. Good if you like getting messy documents to parse cleanly and proving the result holds up.
3 contributors · 2 open
Build the provenance and sources retrieval and the layer that combines the different kinds of evidence into one cited rationale. Good if you like grounded, auditable systems.
2 contributors · 2 open
Build the part of the system that protects a person's primary commitments so nothing else can crowd them out. Good if you like building things that fail safe.
1 contributors · 2 open
Owns the research question and the paper end to end, with faculty mentorship.
4 contributors · 3 open
Help survey and synthesize part of the literature into the shared draft — how the footprint is measured, where efficiency and scheduling gains come from, or what honest accounting requires. Good if you like turning a pile of papers into a clear argument.
3 contributors · 2 open
Build the hear-and-say layer: native text-to-speech per sentence and on-device speech recognition + pronunciation scoring that closes the repeat loop for non-native, non-reader speakers.
3 contributors · 3 open
Put SafeBite through its paces with real menus and real dietary needs, log what breaks or falls short, and turn it into structured data the team uses to make it safer. Good if you like finding gaps and writing them up clearly.
team of 4 · 4 open
