hey, I'm Awais
AI Engineer with 3+ years taking Generative AI systems from prototype to production — enterprise RAG platforms, LLM fine-tuning, and scalable FastAPI services on Azure and GCP. Google-certified Professional Data Engineer, currently pursuing an M.Sc. in Artificial Intelligence, and experienced in GDPR- and EU AI Act-compliant deployments.
let's connect
Ingolstadt, Germany
Experience & Education
Building LLM-powered conversational-intelligence features — call-transcription analysis, summarization, and real-time agent assist — for a European cloud-communications platform. I design RAG and agentic workflows over product and customer-interaction data with GDPR- and EU AI Act-compliant handling, and ship the Python/FastAPI inference microservices behind them with containerized CI/CD and automated quality evaluation.
Graduate study in AI, pursued part-time while working as an AI Engineer.
Architected and deployed an enterprise RAG platform on Terraform-provisioned Azure (FastAPI, Azure AI Search, Docker), with a multi-stage retrieval pipeline of dense vector search plus cross-encoder reranking; fine-tuned Llama-3-8B (QLoRA/Unsloth) to 98% valid-JSON extraction and quantized to GGUF for cost-efficient self-hosted inference. Also built the FastAPI backend of an automotive recommendation engine (NLP query parsing, VIN detection, live data enrichment) through to a client-facing demo, delivered a Jira ticket-analytics solution (.NET + Power BI) and Tableau HR dashboards, and drove technical pre-sales — scoping requirements, building proof-of-concepts, and presenting architectures that converted prospects into signed projects.
Developed Python automation and Jenkins CI pipelines for automotive software releases, cutting manual integration effort by 50% and streamlining OEM release cycles and Artifactory artifact management.
Applied machine learning and clustering (K-means, Fuzzy c-means, Affinity Propagation) to large-scale unlabelled vehicle-trajectory data from the rounD dataset — recorded at three German roundabouts — to identify functional driving patterns for smart-infrastructure and automated traffic. Found that a vehicle's spatial properties strongly predict its roundabout exit, and that velocity profiles cluster tightly by exit, making velocity a reliable predictor of future behaviour.
Projects
spanscore ↗
Open-source eval harness that scores RAG pipelines and AI agents from their OpenTelemetry traces: retrieval metrics, trajectory evaluation, LLM-as-judge with a built-in calibration module (judge vs. human labels), and a paired-bootstrap CI gate that blocks only statistically significant regressions. Ships with a fully reproducible benchmark — committed traces and judge cache re-score without an API key.
Enterprise RAG Platform ↗
Production RAG platform on Terraform-provisioned Azure. Dense vector search over Azure AI Search plus cross-encoder reranking over a naive top-k baseline, served through FastAPI microservices with GDPR-compliant data handling. What a pipeline upgrade like this actually buys, measured properly, is in the writing section below.
sales-research-agent ↗
Provider-agnostic sales-research agent with a custom MCP server over a mock CRM. Researches firmographics, detects buying signals, finds decision-makers, and drafts outreach — with a code-enforced guardrail that every fact traces back to a real tool result. Claude and OpenAI swap behind one protocol.
GithubRepoAssistant ↗
LLM-powered assistant that answers natural-language questions about any public GitHub repository. Built on Pydantic AI with ten focused tools over the GitHub REST API that the model chains automatically to answer questions like "which open issues look stale?"