Skip to content
View darrshangovender's full-sized avatar

Block or report darrshangovender

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.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. 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
darrshangovender/README.md
Darrshan Govender — Senior AI Engineer · LLM/RAG · Full-Stack · Durban GMT+2
About  ·  Currently building  ·  Results  ·  Projects  ·  Open source  ·  Benchmark  ·  Reading  ·  Skills  ·  Hire me

👋 About

I'm a senior AI engineer building production LLM systems — natural-language analytics, retrieval-augmented chatbots, multi-agent pipelines, test-time reasoning compute, and the data infrastructure beneath them. I run Agulhas Code, a Durban engineering studio shipping AI features for SMEs across South Africa.

The thread through my work: treat AI like any other production system. Structured outputs (Pydantic at every LLM boundary), eval-gated CI (no prompt change merges without passing the harness), guardrails by default (sqlglot AST, citation-required prompts, exception queues, read-only roles), full observability (token/cost/latency per call). The frameworks are easy; the discipline is what ships.

Available now for fractional or contract AI work. Full EMEA timezone overlap, 4 hours of US Eastern. Async-first, written-first, deliverable-shaped.


🚀 Currently building

Test-time reasoning compute. Five published strategies (CoT, Self-Consistency, Decomposition, ToT-Lite, Direct) behind one interface, adjudicated by a critic LLM with calibrated confidence + hard budget guards.

reasoning · test-time-compute · pydantic

Production-grade multi-agent system with structured Pydantic handoffs, shared workspace memory, full trace observability. Planner-Researcher-Writer-Critic pipeline.

agents · multi-agent · pydantic

Knowledge-graph-augmented RAG: LLM entity+relation extraction, alias-merged graph store, hybrid vector kNN + graph BFS retrieval with score blending.

rag · knowledge-graph · retrieval


📊 Selected results from production work

~94%

Benchmark accuracy
InsightEngine · NL→SQL
0 destructive incidents

> 0.95

Faithfulness
RAG Chatbot
Recall@5 > 0.85

0.87

ROC-AUC
Churn classifier
top-decile precision 0.62

99.9%+

Uptime
across live client systems

Sub-second

Query latency
from minutes · multi-million-row Postgres

0.41

Recall@10
Recommender
vs 0.18 baseline


🏗️ Production projects

Project What it does Headline result
InsightEngine NL→SQL analytics over multi-table warehouses with sqlglot AST guardrails ~94% accuracy · 0 destructive incidents
RAG Chatbot Production support bot · hybrid retrieval (cosine + BM25) · citation-guarded Faithfulness > 0.95 · Recall@5 > 0.85
Churn & MRR Forecasting XGBoost churn classifier + Prophet MRR forecast for a SaaS client ROC-AUC 0.87 · Top-decile precision 0.62
Recommendation Engine Hybrid content + collaborative recommender for an e-commerce client Recall@10 = 0.41 vs 0.18 baseline
Lead Scorer B2B lead-ranking with LR baseline + XGBoost ranker, scores pushed to CRM Top-decile precision ~0.6
Document-Intelligence OCR → LLM extraction → Pydantic schema validation → human-review queue Replaces manual data entry

🧰 Open-source tooling

Reusable patterns extracted from production work, plus the things I wish existed when I started:

Repo What it does
thinking-loop Test-time reasoning compute · 5 strategies + critic adjudicator + confidence calibration
multi-agent-orchestrator Multi-agent with structured Pydantic handoffs, workspace memory, full trace observability
rag-graph Knowledge-graph-augmented RAG · entity extraction · hybrid vector + graph retrieval
rag-eval-harness Production evals for RAG · faithfulness, recall@k, latency, cost · runs in CI · gates merges
prompt-eval-toolkit A/B test prompt versions with paired-bootstrap p-values · fail-the-build on regression
prompt-versioner Git-style version control for prompts · hash-stable weighted A/B routing · CLI + library
llm-cost-tracker Token / cost / latency observability per LLM call · SQLite store · CLI for stats
semantic-cache Production semantic cache for LLM responses · pgvector kNN · saves 30–80% on chatbot workloads
sql-guardrails Make LLM-generated SQL safe to execute · sqlglot AST + EXPLAIN cost limits
agent-tool-router LLM tool-use router · two-stage embedding-then-LLM with explicit refusal fallback

🧪 thinking-loop — reproducible benchmark

Hand-curated 40-question reasoning benchmark, claude-sonnet-4-5 for strategies, claude-opus-4-7 as adjudicator. Re-run on your machine with cd benchmarks && python run.py.

Strategy Accuracy Median latency Median cost / Q
Direct (baseline) 67.5% 1.1s $0.004
ChainOfThought 80.0% 2.4s $0.011
Decomposition 85.0% 4.8s $0.019
SelfConsistency (n=5) 87.5% 6.7s $0.045
ToTLite (b=3, d=3) 90.0% 9.2s $0.061
ThinkingLoop (all + adjudicator) 92.5% 11.4s $0.078

The Loop wins because the adjudicator catches the 1-2 questions per run where the strongest single strategy gets it wrong but another nailed it. 3.7× cost over baseline for +25 percentage points accuracy on hard reasoning.


📚 Now thinking about

What I'm chewing on right now — papers, posts, and threads shaping the work above:

  • Test-time compute & reasoning — Wang et al. Self-Consistency; Yao et al. Tree of Thoughts; Shinn et al. Reflexion; OpenAI o1-style scaling. Spawned thinking-loop.
  • Agentic systems with rigour — Anthropic's Building effective agents guide; deep dives on structured tool-use vs freeform. Shapes multi-agent-orchestrator.
  • Retrieval beyond vectors — GraphRAG (Microsoft), HippoRAG, hybrid sparse+dense+graph. Drives rag-graph.
  • Eval-driven dev — Hamel Husain's Your AI product needs evals; Eugene Yan's eval-system patterns. Why rag-eval-harness ships with a CI workflow.
  • Production cost discipline — semantic caching saves 30-80% on real chatbot traffic; cost-per-feature is the metric that makes AI products actually profitable. The reason for semantic-cache and llm-cost-tracker.

Updated regularly · last revision {{lastmod}}


🛠️ Skills

My Skills

AI & ML   ·   OpenAI · Anthropic · LangChain · Pydantic · scikit-learn · XGBoost · Prophet · sentence-transformers · pgvector

Data   ·   PostgreSQL · pgvector · MySQL · SQLite · dbt · window functions · CTEs · EXPLAIN-tuning

Cloud & MLOps   ·   AWS (EC2, S3, Lambda, RDS) · Vercel · Docker · GitHub Actions CI/CD · structured logging


🧭 How I work

  • Ship end-to-end — discovery, architecture, build, deploy, monitor. Not just the AI bit.
  • Async-first — written specs, weekly status updates, comfortable owning ambiguous problems.
  • Test what you ship — every prompt change runs an eval suite before merge.
  • Defensive by default — guardrails, citations, exception queues, read-only roles.
  • Treat prompts like code — versioned, diffable, rollback-able, A/B routable.
  • Structured > freeform — Pydantic at every LLM boundary; fail fast on schema mismatch.
  • Spend compute deliberately — multi-strategy reasoning when accuracy matters, cheap baselines when it doesn't.

📈 GitHub activity


💼 Hire me

🏗️ Fractional AI Lead

10–30 hrs/week
Embedded in your team's standups. Own the AI roadmap, prompt discipline, eval gates. Rate on application.

🛠️ Contract Build

Project / day-rate
Scoped LLM features, RAG systems, data pipelines, evals. From discovery to shipped + monitored.

🎯 Architecture Review

Single engagement
Sit with your team for a week. Map the AI surface. Leave with a written report + 30-day plan.

📧 darrshangovender@gmail.com   ·   🌐 agulhascode.co.za   ·   📍 Durban, South Africa (GMT+2)


Open to: EMEA & UK remote · worldwide contract · US ET overlap roles · founding / lead AI · fractional retainers

If your team needs a senior AI engineer who can ship production LLM systems with the eval and observability discipline of a senior backend engineer — let's talk.

Pinned Loading

  1. churn-forecasting churn-forecasting Public

    XGBoost churn classifier + Prophet MRR forecaster for a SaaS client. ROC-AUC 0.87.

  2. insightengine insightengine Public

    Natural-language SQL analytics over a multi-table warehouse — LLM query-planner with sqlglot AST guardrails. ~94% benchmark accuracy.

  3. prompt-eval-toolkit prompt-eval-toolkit Public

    A/B test prompt versions on a dataset with bootstrap p-values. Fail-the-build on regression.

    Python

  4. rag-chatbot rag-chatbot Public

    Production RAG support chatbot - hybrid retrieval, citation-guarded responses, faithfulness eval.

  5. rag-eval-harness rag-eval-harness Public

    Production-grade evals for RAG systems - faithfulness, relevance, recall@k. Runs in CI.

    Python

  6. recommendation-engine recommendation-engine Public

    Hybrid content + collaborative recommender for e-commerce. Recall@10 = 0.41 vs 0.18 baseline.