METAHEURISTICBook a call

Hire an agentic AI engineer who ships to production.

Alexander Myasoedov builds LLM agents, retrieval systems, and the evals and guardrails that keep them alive after launch. Contract, fractional, or embedded with your team - usually 2 to 10 weeks from demo to production.

4.6k
GitHub stars across public work
2-10 wk
Demo to production
100%
Code, prompts and IP yours
2012
Shipping open source since
[What you get]

Most AI projects do not fail at the demo. They fail in the ninety days after it, when the prototype meets real users, real documents, real permissions and a real bill. The gap between “the model can do this” and “this runs in production” is engineering work, and it is specific: control flow, retrieval quality, evaluation, guardrails, cost, latency, observability, rollback.

That gap is what I am hired to close.

What you are hiring

  • Agent systems that terminate. Planning loops with explicit budgets, tool contracts, retries and cutoffs - so a bad step costs you a few seconds, not a runaway bill or a corrupted record.
  • Retrieval that respects your org chart. Permission-aware RAG, hybrid search, chunking that matches your document reality, and freshness you can reason about.
  • Evals before opinions. A golden set, a regression gate in CI, and a number that tells you whether last night’s prompt change made things better or worse.
  • Guardrails and red-teaming. Prompt injection, tool abuse, data exfiltration and jailbreaks are treated as a threat model, not a disclaimer. I maintain an open-source LLM red-teaming kit used by other teams to test their own systems.
  • AgentOps. Traces, replay, cost per task, failure taxonomies, and a rollback path that does not require a heroic night.
  • A team that can take over. Handover is the deliverable, not an afterthought. Your engineers should be able to extend the system without me in the room.

What you are not hiring

Not a wrapper vendor. Not a platform with seats to license. Not a research lab that returns a paper. Not a body shop that staffs four juniors against a statement of work and calls the overhead “velocity.”

One senior engineer, working directly with your team, on a scope small enough to finish and specific enough to verify.

How engagements usually run

  1. Twenty-minute call. What you are trying to build, what is already in place, what “done” means. Free, and you get a straight answer even if the answer is “you do not need this.”
  2. Discovery Sprint - 2 to 4 weeks. Architecture, a working thin slice, a security pre-check, cost and latency modelling, and a roadmap your board can read. Fixed fee, credited against the build.
  3. Build - 4 to 10 weeks. Embedded with your team, shipping behind flags, with evals gating every release.
  4. Handover or fractional. Either your team owns it outright, or I stay on a recurring block for the next thing.

Full detail on scope, pricing structure and commitment lengths is on the rates and engagement models page.

[Start here]

Pick the role you are actually hiring for.

[Public work]

The code is public. Go read it.

Star counts as of September 2026. Live numbers on github.com/msoedov.

Hiring questions.

What does an agentic AI engineer actually do? +

Designs and ships systems where an LLM plans, calls tools, and acts over multiple steps - then makes that loop observable, testable and safe enough to point at real users and real data. In practice that is control flow, tool contracts, retrieval, evals, guardrails, cost and latency budgets, and the on-call story. See the full job description.

Contract, fractional, or full-time? +

Contract and fractional. A typical engagement is a fixed-scope Discovery Sprint followed by an embedded build, or a recurring fractional block for teams that already have engineers and need senior AI judgement in the room. Full-time employment is not on the table - see rates and engagement models.

Who owns the code? +

You do, contractually, from day one - code, prompts, evals, infrastructure and IP. There is no runtime to license and no platform to get locked into. If the engagement ended tomorrow your systems keep running and your team keeps shipping.

Can you work on-premise or in our cloud? +

Yes. Sovereign and on-premise deploys are a normal request, especially in regulated environments. Open-weight models, your VPC, your keys, your logs. Nothing has to leave your perimeter.

How fast can we start? +

Booking is per quarter with limited slots. The first step is a 20-minute call - you leave it with an honest read on whether your use case is buildable at your budget, whether or not we work together.

Need an agentic AI engineer this quarter?

Contract, fractional, or embedded with your team. Start with a 20-minute call - you leave it with an honest read on whether your use case is buildable, whatever happens next.