a
annas_7_

Annas M

@annas_7_
4,0(11)

AI Engineer Building Scalable LLM, RAG, and Conversational AI

Pakistan
Engels, Urdu
Sommige informatie wordt in het Engels weergegeven.
Over mij
AI and LLM Engineer with hands-on experience building production-ready AI systems across legal tech and enterprise workflows. I’ve worked full-time on a multilingual legal AI platform processing 450 plus real legal documents using hybrid RAG, advanced chunking, and agent-based architectures. My work includes document AI, conversational bots, text and voice systems, cloud deployments and scalable backend services. I focus on reliable, secure, and maintainable AI solutions that deliclver real business value.... Lees meer

Skills

a
annas_7_
Annas M
offline • 
Gemiddelde reactietijd: 6 uur

Bekijk mijn diensten

AI chatbot development
I will create ai chatbots using llms ,rag, agentic ai, PDF chatbot
3,7(3)
AI-integraties
I will create an ai assistant to query your database using natural language

Werkervaring

AI Engineer

Niblon • Fulltime

Apr 2022 - Oct 20253 yrs 6 mos

• Designed and deployed 10+ AI and RAG systems with adaptive memory and reflexive reasoning • Built LLM-as-Judge pipelines and Human-in-the-Loop evaluators, improving accuracy by 25% • Enhanced RAG retrieval precision with embedding quantization, adaptive chunking, and hybrid ranking, reducing response latency by 40% • Applied MLOps practices (monitoring, cost optimization, model iteration) and optimized inference latency through hybrid retrieval and caching. • Developed voice-enabled AI agents using Whisper (STT) and ElevenLabs (TTS), processing 10K+ voice interactions monthly with 92% transcription accuracy • Researched Agent-to-Agent and MCP-based reflexive reasoning for scalable automation • Architected and deployed hybrid RAG systems with multi-step retrieval pipelines, combining dense embeddings (FAISS) and sparse retrieval (BM25) to achieve 35% improvement in answer relevance • Built custom evaluation frameworks using RAGAS metrics to monitor and improve RAG performance • Implemented multi-step reasoning chains with LangChain and custom tool-calling mechanisms, handling complex queries requiring 3-5 sequential API calls • Optimized embedding generation and caching strategies, reducing API costs by 45%

11 Reviews
4,0

(9)
(1)
(0)
(0)
(1)
Specificering van de beoordeling
  • Communicatieniveau van de freelancer
    4
  • Kwaliteit van de levering
    3,7
  • Waarde van de levering
    3,7
1-5 van 11 reviews
Sorteer op
Meest relevant
    A

    aaawa1

    Terugkerende klant

    SA

    Saoedi-Arabië

    1

    I don't like the work

    Tot maximaal US$ 50

    Prijs

    11 dagen

    Looptijd

    gig

    AI chatbot development

    A

    Reactie van de freelancer

    Nuttig?
    Ja
    Nee
    A

    aaawa1

    Terugkerende klant

    SA

    Saoedi-Arabië

    5

    I recommend dealing with him, he is the best.

    US$ 50-US$ 100

    Prijs

    5 dagen

    Looptijd

    gig

    AI chatbot development

    Nuttig?
    Ja
    Nee
    R

    rmuranaka

    Terugkerende klant

    US

    Verenigde Staten

    5

    Helped build a custom LLM model using gpt-4

    US$ 200-US$ 400

    Prijs

    2 dagen

    Looptijd

    gig

    AI chatbot development

    Nuttig?
    Ja
    Nee
    D

    dodgemeapp

    US

    Verenigde Staten

    5

    It was a pleasure to work with Annas. He contacted me shortly after I reached out to him and he understood the scope of work and all the instructions I gave him. Annas delivered the final product ahead of time. I’ll definitely reach out to Annas for future support.

    Nuttig?
    Ja
    Nee
    P

    prejusaazares

    Terugkerende klant

    PH

    Filippijnen

    5

    asusual, amszing work, great service

    Werkvoorbeeld
    Nuttig?
    Ja
    Nee