Skip to content
View sharmis-tp's full-sized avatar

Block or report sharmis-tp

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
sharmis-tp/README.md

Senior Rust Engineer · AI/ML Infrastructure

The systems layer under machine learning: training libraries, checkpoints, agent evaluation and LLM observability.

Rust Python TypeScript OpenTelemetry Tokio

followers email open to remote work


whoami

I've been building software since 2018, most of it in Rust: async services, FFI, memory allocators and protocol code that has to stay correct under load.

Today I work where that background matters most in AI: the infrastructure that models and agents run on. That means numerical correctness in training code, checkpoints that survive a crash, evaluation scores you can trust, and traces that tell you why an agent did what it did.

Models are only as reliable as the systems that train, evaluate and serve them.

What I work on

Area What I focus on
Training library internals Optimizer math (RMSprop variance, epsilon placement), weight initialization (Kaiming/Xavier), RNN input validation, numerically stable edge cases
Checkpointing & data integrity Atomic checkpoint writes, batched tensor serialization, verified dataset downloads
Agent evaluation Scoring and weighting of eval dimensions
LLM observability OpenTelemetry spans for agent and tool events, error capture in LangChain tracing, token-usage parsing
Forecasting & anomaly detection Exogenous-feature support in time-series foundation-model pipelines
Systems foundations Tokio, cancellation safety, backpressure, zero-copy I/O, FFI and unsafe audits

Open-source work in AI/ML

All links go to my own pull requests.

Merged

Project Contribution
FastNN: neural-network library in Rust + CUDA Reject zero-length sequences in LSTM/GRU with a clear message
Verify MNIST download integrity before using a cached file
jamjet: safety layer for AI agents Fix DimensionScores.composite() weight normalization
Add OpenTelemetry span attributes for coordinator and agent-tool events

In review

Project Contribution
FastNN Fix centered RMSprop: clamp variance, move eps outside sqrt
Atomic checkpoint writes · Batch tensor I/O in checkpoint serialization
Assert fan_in > 0 in Kaiming/Xavier init
foundationforecast: time-series foundation models Accept X_df and futr_exog_list in detect_anomalies
lemma: LLM tracing Record handled LangChain tool errors as span errors
oxtrace: LLM usage tracing Parse usage from gzip-encoded responses
runanywhere-sdks: on-device AI SDKs Typecheck core test files

Systems & distributed work

Merged contributions to py-libp2p, papi-console (Polkadot), circom, beancount-language-server, perun-ckb-backend, uor-addr and metal2vk.

Own repositories: smalloc (memory allocator for Solana programs), Dbgeng-sys (Rust FFI bindings for the Windows debugger engine), Solana-Credit-Score, AsyncCSVX.

How I work

01. Measure, then optimize. Throughput, tail latency and allocations, not guesses.

02. Make failure boring. Writes are atomic, inputs are validated at the boundary, and errors say what to do next.

03. Trust numbers only when they're tested. An eval score or a loss curve is only as good as the code that computes it.

04. Small, reviewable changes. Every PR above is scoped to one problem and easy to review.


Open to remote roles and contracts with AI/ML startups: ML infrastructure, inference, evaluation and Rust performance work.

Pinned Loading

  1. awesome-rust awesome-rust Public

    Forked from rust-unofficial/awesome-rust

    A curated list of Rust code and resources.

    Rust 2 1

  2. Solana-Credit-Score Solana-Credit-Score Public

    Solana Credit Score shows which validators give the best staking rewards.

    Rust 1

  3. omnibus omnibus Public

    This repo contains code for managing and testing token-related programs

    Rust

  4. cross cross Public

    Forked from cross-rs/cross

    “Zero setup” cross compilation and “cross testing” of Rust crates

    Rust

  5. slint slint Public

    Forked from slint-ui/slint

    Slint is an open-source declarative GUI toolkit to build native user interfaces for Rust, C++, JavaScript, or Python apps.

    Rust

  6. smalloc smalloc Public

    A small memory allocator for Solana programs

    Rust