Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I’m an AI Engineer focused on production-ready LLM systems, RAG pipelines, voice AI, and agentic architectures. I build and ship reliable conversational AI—from retrieval and evaluation (including hallucination detection/confidence scoring) to deployment, monitoring, and reliability improvements. I enjoy owning both the engineering and client delivery sides of conversational AI. I have hands-on experience with hybrid retrieval, prompt evaluation/benchmarking, streaming/latency optimization, and integrating APIs/webhooks across platforms like OpenAI, ElevenLabs, Retell AI, and MCP workflows.…I’m an AI Engineer focused on production-ready LLM systems, RAG pipelines, voice AI, and agentic architectures. I build and ship reliable conversational AI—from retrieval and evaluation (including hallucination detection/confidence scoring) to deployment, monitoring, and reliability improvements. I enjoy owning both the engineering and client delivery sides of conversational AI. I have hands-on experience with hybrid retrieval, prompt evaluation/benchmarking, streaming/latency optimization, and integrating APIs/webhooks across platforms like OpenAI, ElevenLabs, Retell AI, and MCP workflows.

Hamza Jaffer Brohi

AI Engineer, AI Trainer, Software Engineer, +1





I’m an AI Engineer focused on production-ready LLM systems, RAG pipelines, voice AI, and agentic architectures. I build and ship reliable conversational AI—from retrieval and evaluation (including hallucination detection/confidence scoring) to deployment, monitoring, and reliability improvements. I enjoy owning both the engineering and client delivery sides of conversational AI. I have hands-on experience with hybrid retrieval, prompt evaluation/benchmarking, streaming/latency optimization, and integrating APIs/webhooks across platforms like OpenAI, ElevenLabs, Retell AI, and MCP workflows.…I’m an AI Engineer focused on production-ready LLM systems, RAG pipelines, voice AI, and agentic architectures. I build and ship reliable conversational AI—from retrieval and evaluation (including hallucination detection/confidence scoring) to deployment, monitoring, and reliability improvements. I enjoy owning both the engineering and client delivery sides of conversational AI. I have hands-on experience with hybrid retrieval, prompt evaluation/benchmarking, streaming/latency optimization, and integrating APIs/webhooks across platforms like OpenAI, ElevenLabs, Retell AI, and MCP workflows.

Available to hire

I’m an AI Engineer focused on production-ready LLM systems, RAG pipelines, voice AI, and agentic architectures. I build and ship reliable conversational AI—from retrieval and evaluation (including hallucination detection/confidence scoring) to deployment, monitoring, and reliability improvements.

I enjoy owning both the engineering and client delivery sides of conversational AI. I have hands-on experience with hybrid retrieval, prompt evaluation/benchmarking, streaming/latency optimization, and integrating APIs/webhooks across platforms like OpenAI, ElevenLabs, Retell AI, and MCP workflows.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Intermediate

Intermediate

Work Experience

Technical Customer Success Manager (Voice AI & Delivery) at DialogX IO

April 1, 2026 - Present

Owned prompt configuration, QA, and agent evaluation across production voice agents, including call-quality scoring, latency tuning, edge-case testing, and API/webhook debugging using OpenAI, ElevenLabs, Retell AI, and MCP workflows. Led end-to-end technical delivery of AI voice agents across a 100+ client portfolio, from requirements gathering and intake through go-live and post-launch optimization. Cut average deployment timeline from ~30 days to under 15 days and shipped 30+ production deployments through process improvement and hands-on technical execution. Partnered with AI Engineers, Developers, and RPA Engineers to translate business requirements into production-ready Voice AI solutions and custom workflow integrations.

OpenClaw Automation Engineer (US -Remote) at Umbrella Fund

March 1, 2026 - June 30, 2026

Designed and deployed browser-automation workflows for Amazon seller operations to automate extraction and processing of unshipped orders. Built cross-platform shipping-rate comparison pipelines to optimize fulfillment cost and delivery decisions. Automated inventory and performance tracking into SoStocked for real-time operational metrics.

Backend AI Engineer Intern at Center for Advanced Research in Engineering (CARE)

January 1, 2026 - April 30, 2026

Ran model evaluation and benchmarking to improve response consistency by ~20% through prompt and parameter optimization. Built an automated evaluation framework that increased reasoning coverage by ~35% and reduced evaluation turnaround time by ~25%.

AI Trainer (Freelance, Part-Time) at Mindrift

November 1, 2025 - April 30, 2026

Evaluated 500+ LLM responses and improved reasoning accuracy through structured feedback and error classification.

AI Research Intern at Operexa Pvt Ltd

June 1, 2025 - September 30, 2025

Ran LLM optimization experiments that improved retrieval relevance and response quality, contributing to internal RAG pipeline development.

AI Automation Intern at Appity Pvt Ltd

June 1, 2024 - August 31, 2024

Built Python + LLM automation systems that reduced manual document-processing time by ~30%, saving 15+ hours per month.

Founder & Operator at RYU'S Gaming Zone

February 1, 2023 - Present

Founded and operated a gaming facility serving ~1,000+ customers monthly at ~85% repeat rate. Owned operations, pricing strategy, and customer experience.