Skip to content

Complete technical profile

AI Engineering — Complete Technical Profile

Peter McCann Strain builds the whole system: governed AI platforms, private assistant infrastructure, patent-intelligence products, real-time voice operations, evaluation harnesses, production workflows, and research methods.

Patent-intelligence venture

Praviar

In-production pharmaceutical patent-intelligence venture, going to market, with fixed checks, bounded legal reasoning support, and private implementation detail.

Voice-operations venture

Conversico

In-production AI receptionist venture going to market, focused on missed-call recovery, booking support, privacy, and launch-gated operations.

Enterprise agentic AI at SThree

Aurum

Multi-agent orchestration, synthetic candidate systems, evaluator architecture, self-improvement research, reviewable state, fairness diagnostics, red-team layers, audit records, and production control.

8 agents · private daily use

Personal Assistant AI

An ongoing independent private assistant with durable memory, proactive background work, and quality monitoring.

0 mismatches · 50 runs

Datamise legal infrastructure

Co-founded Datamise; built claims infrastructure and a valuation engine that matched a separate calculator penny-for-penny.

P0–P12 patterns

Deep-research benchmark

Benchmark study of around 13 orchestration patterns with judge-reliability panels, citation audits, and equivalence testing.

180× cheaper

Skills Taxonomy pipeline

CV skill tagging rebuilt around retrieval, filters, calibration, and a 7 kB head — zero LLM calls in the production hot path.

Oxford · Astroscale · CivTech

Research-to-product range

An 89%-accurate medical-imaging classifier, satellite sim-to-real vision, and public-sector AI strategy across hard domains.

What the engineering actually looks like

The throughline is range under constraint: regulated hiring workflows, reviewable legal calculations, satellite computer vision, and Oxford medical-imaging research all demanded traceability rather than a demo.

  • Founding AI Engineer at SThree: architected Aurum as enterprise agentic AI employer work, contributed to £25M of board investment, and grew the AI team from 2 to 10.
  • Built Personal Assistant AI independently as a private assistant case study with durable memory, proactive support, and quality monitoring.
  • Built Praviar and Conversico as current founder ventures: one around bounded pharmaceutical patent intelligence, the other around real-time AI voice operations with Greeta as the voice agent.
  • Cut SThree CV skill-tagging cost 180× by moving validation from LLM calls to retrieval, deterministic filters, calibration, and a 7 kB head.
  • Co-founded Datamise, where a two-person team built owned claims infrastructure for GMB equal-pay campaigns and the SettleMise valuation engine.
  • Oxford DPhil: built a whole-slide placental histology pipeline with an 89%-accurate 8-class cell classifier.

Where Peter fits best

The ideal role is senior or staff-level AI engineering where architecture, evaluation, governance, and product delivery all matter.

  • Agentic systems with human-in-the-loop approvals and observable state transitions.
  • Applied ML systems where statistical claims need to survive scrutiny.
  • Cross-functional environments with legal, compliance, operations, product, and engineering stakeholders.

Continue exploring

Related work

Read all writing