LLM Engineer / AI Engineer

YO IT Consulting; Hyderabad; Hybrid; INR 1,500,000 - 2,000,000; Full time

Job summary

A leading IT consultancy in Hyderabad is seeking an experienced LLM Engineer / AI Engineer to design and optimize advanced Large Language Model systems. The successful candidate will have a strong background in RAG architectures and experience deploying AI solutions in production environments. Responsibilities include engineering scalable LLM pipelines, developing evaluation frameworks, and optimizing performance in high-throughput settings. The position offers a hybrid work model, requiring three days in-office per week.

Qualifications

• Proven experience as an LLM Engineer / AI Engineer.
• Strong hands-on expertise with RAG Architecture.
• Experience deploying AI systems in production environments.

Responsibilities

• Design and optimize LLM pipelines.
• Architect and maintain RAG systems.
• Develop and test prompt templates.

Skills

Experience with RAG Architecture

Expertise in Python and AI frameworks

Understanding of embeddings and tokenization

Experience with vector databases

Knowledge of cloud platforms

Deployment in production environments

Education

Bachelor of Engineering / Bachelor of Technology (B.E. / B.Tech.)

Tools

LangChain

LlamaIndex

Pinecone

Weaviate

FAISS

Job description

Experience: 5-8 Years

Work Mode: Hybrid (3 days Work From Office)

Job Title: LLM Engineer / AI Engineer

Location: Hyderabad

Role Overview

We are looking for a highly skilled LLM / AI Engineer to design, build, and optimize advanced Large Language Model (LLM) systems. The ideal candidate will have hands‑on experience with RAG architectures, autonomous agents, and production‑grade AI deployments in high‑performance environments such as Trading, FinTech, or Global Logistics. You will play a critical role in developing intelligent AI agents capable of real‑time reasoning, tool usage, and contextual retrieval across internal knowledge systems and trading platforms.

Key Responsibilities

Model Engineering

• Design, implement, and optimize scalable LLM pipelines.
• Work with proprietary models (e.g., OpenAI, Anthropic) and open‑source models (Llama, Mistral).
• Evaluate and select models based on cost, latency, accuracy, and performance benchmarks.
• Fine‑tune and adapt models for domain‑specific use cases.

RAG Architecture Development

• Architect and maintain advanced Retrieval‑Augmented Generation (RAG) systems.
• Integrate vector databases and real‑time data sources.
• Enable contextual retrieval from internal documentation, customer records, and trading platform data.
• Improve retrieval quality, embedding strategies, and chunking mechanisms.

Prompt Engineering & Optimization

• Develop, test, and version‑control structured prompt templates.
• Apply techniques such as Few‑Shot Learning, Chain‑of‑Thought, ReAct, and System Prompt tuning.
• Continuously optimize prompts to reduce hallucinations and improve reasoning depth.

Evaluation & Testing Frameworks

• Build LLM‑as‑a‑Judge evaluation systems.
• Develop automated testing pipelines to measure hallucination rates, toxicity, factual accuracy, and response consistency.
• Establish validation protocols before deploying agents to non‑production and production environments.

Tool‑Use & Agentic Logic

• Implement reliable tool‑calling frameworks enabling agents to call APIs, execute database queries, and trigger specialized functions.
• Design safe execution layers and guardrails.
• Build autonomous and semi‑autonomous AI agents for real‑world workflows.

Latency & Performance Optimization

• Optimize inference pipelines for near real‑time responses.
• Improve retrieval speed, caching strategies, and concurrency handling.
• Monitor and reduce token usage and operational costs.

DevOps & LLMOps

• Implement monitoring frameworks for model performance and drift detection.
• Set up observability tools for prompt performance, cost tracking, and failure analysis.
• Manage CI/CD pipelines for AI models and prompt deployments.

Required Skills

• Strong hands‑on experience with RAG Architecture.
• Proven experience working as an LLM Engineer / AI Engineer.
• Expertise in Python and AI frameworks (LangChain, LlamaIndex, etc.).
• Experience with vector databases (Pinecone, Weaviate, FAISS, etc.).
• Knowledge of cloud platforms (AWS, GCP, Azure).
• Strong understanding of embeddings, tokenization, and inference optimization.
• Experience deploying AI systems in production environments.

Additional Preferred Qualifications

• Experience in high‑throughput environments (Trading, FinTech, Global Logistics).
• Prior experience building and deploying autonomous agents at scale.
• Familiarity with the Claude ecosystem and OpenClaw.
• Experience working with streaming data and real‑time systems.
• Strong problem‑solving and system design skills.
• Experience working in high‑throughput, low‑latency environments such as Trading, FinTech, Capital Markets, or Global Logistics, where performance, scalability, and reliability are critical.
• Proven experience designing, building, and deploying autonomous or semi‑autonomous AI agents in production environments, including tool‑use orchestration, workflow automation, and safe execution frameworks.
• Familiarity with the Claude ecosystem (Anthropic models) and experience leveraging its capabilities for reasoning‑heavy, safety‑focused applications.
• Exposure to the OpenClaw ecosystem and related agentic frameworks for building modular, extensible AI systems.

Education Requirement

Bachelor of Engineering / Bachelor of Technology (B.E. / B.Tech.) in Computer Science, Artificial Intelligence, Data Science, or related field.