AI Engineer-LLM Integration/Platform Observability

3 days ago


Hyderabad, Telangana, India Kiash Solutions LLP Full time ₹ 15,00,000 - ₹ 25,00,000 per year

Exp -- 4+ Years

Shift--
2.00 PM to 11:30 PM IST

Mandatory--
Python with LLM Ops

Job Description--

We are looking for a
hands-on AI Engineer
with strong expertise in
LLM integration, platform observability, performance optimization, and API development
. The ideal candidate will work on critical platform enhancements, including
LLM API integrations, observability pipelines, structured search algorithms, and performance scaling
for customer's AI platform and related components.

You will collaborate with cross-functional teams to develop robust, scalable solutions, modernize our logging and monitoring infrastructure, and integrate advanced AI capabilities into production workflows.

Key Responsibilities:

1. LLM Integration & API Development

  • Develop and maintain
    LLM API integration test cases
    for core model availability.
  • Refactor and reorganize
    LLM API code (e.g., )
    for better maintainability.
  • Add support for
    Vertex AI batch generation
    and batch transcription processing.
  • Implement
    multi-step structured search algorithms
    and tie model IDs to relevant endpoints.
  • Explore and integrate emerging technologies like
    LightRAG, SurrealDB, Neo4j, and Puppygraph
    for structured search.

2. Platform Observability & Performance

  • Implement
    Splunk OpenTelemetry (OTel)
    integration for monitoring and metrics.
  • Evaluate and integrate
    Arize AI
    for observability and model evaluation frameworks.
  • Optimize
    logging decorators
    ,
    memory profiling
    for unit tests, and enhance
    APM (Application Performance Monitoring)
    solutions.
  • Drive
    scaling and performance optimization
    for the JedAI platform.

3. Platform Integration & Testing

  • Implement
    platform integration and availability testing frameworks
    .
  • Centralize
    Postman test cases
    for integration testing.
  • Clean up
    outdated tests
    and modernize
    Docker Compose setups
    for KB API development.
  • Develop
    harness configurations
    for automated testing pipelines.

4. Architecture & Research Spikes

  • Support
    JedAI architecture consulting
    efforts.
  • Conduct
    spike investigations
    on new technologies and frameworks for performance and scalability.
  • Explore
    MCP design
    options for multi-agent orchestration and AI-enhanced workflows.

Required Skills & Experience:

  • Programming:
    Python (must-have), (good to have)
  • AI/ML Integration:
    Hands-on experience with
    LLM APIs (OpenAI, Vertex AI, etc.)
  • Observability & Logging:
    Experience with
    Splunk, OpenTelemetry (OTel), Arize AI
  • Testing & CI/CD:
    Proficiency with
    Postman, Pytest, Docker Compose
  • Data & Search:
    Exposure to
    structured search techniques
    (Neo4j, LightRAG, Graph DBs)
  • Performance Tuning:
    Familiarity with
    memory profiling, performance optimization, and scaling
    techniques
  • Cloud Platforms:
    GCP (Vertex AI), Azure, or AWS experience preferred
  • Collaboration Tools:
    GitHub, Jira, Confluence

Preferred Qualifications:

  • Bachelor's or Master's in Computer Science, AI/ML, or related fields
  • 3–6 years of experience in AI/ML engineering or platform development
  • Prior experience in
    AI observability
    or
    model evaluation pipelines
  • Knowledge of
    Agentic AI frameworks
    and
    multi-step reasoning systems


  • Hyderabad, Telangana, India Veltris Full time ₹ 12,00,000 - ₹ 36,00,000 per year

    Greetings from VeltrisPlease find the details below, and interested candidates can share their updated resumes at asap.Role: Java Full Stack AI/LLM Integration EngineerExperience: 5 to 12 YearsLocation: RemoteWork Mode: RemotePosition Overview:We are on the lookout for a skilled Java Developer with expertise in integrating third-party AI and Large Language...

  • GEN AI Engineer-LLM

    2 weeks ago


    Hyderabad, Telangana, India GEMRAJ TECHNOLOGIES LIMITED Full time

    Sr. LLM Engineer: Gen AI Location-Work from Office - Hyderabad/Gurgaon - 3 days hybrid YoE-5 - 9 Years Start Date: Immediate/Full time Must Have Skills: Machine Learning models & systems Generative AI (LLM) / LLM prompt engineering Building LLM RAG Experience in using langchain or similar tool Turing is looking for people with LLM experience to join us in...


  • Hyderabad, Telangana, India Ekshvaku Tech Innovations Full time ₹ 20,00,000 - ₹ 25,00,000 per year

    Generative AI Engineer (LLMs & RAG) Healthcare SaaSLocation: Remote / Hyderabad (preferred)Experience: 5+ yearsEmployment Type: Full-timeDomain: Generative AI, Healthcare, SaaSAbout the RoleWe are looking for a hands-on Generative AI Engineer with expertise in Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). In this role, you will...


  • Hyderabad, Telangana, India Soothsayer Analytics Full time US$ 1,20,000 - US$ 2,00,000 per year

    We seek a Senior Gen AI Engineer with strong ML fundamentals and data engineering expertise to lead scalable AI/LLM solutions. This role focuses on integrating AI models into production, optimizing machine learning workflows, and creating scalable AI-driven systems. You will design, fine-tune, and deploy models (e.g., LLMs, RAG architectures) while ensuring...

  • AI LLM Engineer

    2 days ago


    Hyderabad, Telangana, India Huemn Full time ₹ 20,00,000 - ₹ 25,00,000 per year

    Job OverviewWe are seeking a Senior AI LLM Engineer to join our team at Huemn in Hyderabad. This is a full-time position that requires expertise in large language models and natural language processing. The ideal candidate will have a strong background in advanced AI technologies, with a focus on retrieval-augmented generation. You will work closely with our...

  • LLM Engineer

    3 weeks ago


    Hyderabad, Telangana, India Ampstek Full time

    Job Role : Sr. LLM Engineer : Gen AILocation : the Role :LLM Engineer : Gen AI. Turing is looking for people with LLM experience to join us in solving business problems for our Fortune 500 customers. You will be a key member of the Turing GenAI delivery organization and part of a GenAI project. You will be required to work with a team of other Turing...

  • Agentic AI Intern

    2 days ago


    Hyderabad, Telangana, India Centella AI Therapeutics Full time ₹ 9,00,000 - ₹ 12,00,000 per year

    Centella AI is an AI-first organization addressing the critical challenges of drug discovery such as cost and time. Our AI platform, CASCADE utilizes Large Language Models (LLMs) to design drug-like molecules with improved safety and efficacy while significantly reducing costs. We are looking for passionate Agentic AI intern interested to work at the...

  • Lead AI Engineer

    1 week ago


    Hyderabad, Telangana, India Weekday AI Full time ₹ 5,00,000 - ₹ 8,00,000 per year

    This role is for Weekday's client.Role OverviewAs the Lead AI Engineer, you will be responsible for spearheading the design, development, and deployment of AI solutions. You will work with various large language models (LLMs)—both open-source and proprietary—optimizing them through fine-tuning, prompt engineering, agentic frameworks, and...

  • Senior AI Engineer

    7 days ago


    Hyderabad, Telangana, India Backbase Full time ₹ 20,00,000 - ₹ 25,00,000 per year

    At Backbase, we're redefining how banks deliver customer experiences by embedding intelligence into every digital interaction. Our Engagement Banking Platform puts the customer first — and behind the scenes, our AI team powers the intelligence that makes it personal, predictive, and responsive.As a Senior AI Engineer – Consultant, you'll be part of our...

  • AI Engineer

    2 days ago


    Hyderabad, Telangana, India Deccan AI Full time ₹ 15,00,000 - ₹ 20,00,000 per year

    Location:Hyderabad (On-site/Hybrid)Company:Deccan AIEmployment Type:Full-TimeExperience:1–3 YearsAbout Deccan AIDeccan AI is at the forefront of building advanced AI solutions for real-world applications. We're passionate about pushing the boundaries of artificial intelligence, natural language processing, and intelligent agent systems. Join us and work...