LLM Engineer

About the Role

You will design, develop, and optimize LLM-powered applications, leveraging modern orchestration frameworks, vector databases, and advanced AI tool integrations. This is a chance to work at the forefront of AI/LLM engineering, building intelligent, scalable, and high-performance solutions that power next-generation interview and career growth platforms.

Key Responsibilities

• Design and build production-grade

  LLM-powered applications

  using

  APIs

  from OpenAI, Claude, and Gemini
• Develop sophisticated AI workflows using

  LangGraph

  ,

  DSPy

  , and advanced tool-use frameworks
• Implement and optimize

  MCP

  (Model Context Protocol) server integrations to extend LLM capabilities
• Architect and deploy

  vector database

  solutions using Qdrant, Milvus, or Pgvector for semantic search and retrieval
• Engineer advanced prompt strategies, orchestration patterns, and tool chaining for maximum accuracy and performance
• Build high-concurrency microservices using

  FastAPI

  with extensive I/O orchestration
• Implement asynchronous programming patterns using asyncio and manage real-time communications via

  WebSockets

  (socket.io)
• Design and maintain

  message queue systems

  using Celery, RabbitMQ, or AWS SQS
• Optimize applications for scalability on Kubernetes, understanding pod autoscaling and resource management
• Collaborate with cross-functional teams to deliver AI-enabled solutions that handle 10k+ concurrent users
• Manage code repositories, CI/CD pipelines, and deployments using Azure DevOps
• Actively participate in Agile ceremonies including sprint planning, daily standups, and delivery reviews
• Work with distributed databases including PostgreSQL, MongoDB, Databricks, and Iceberg

Required Qualifications

Education

• Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, or related technical field

Experience

• 4+ years of professional software development experience
• 2+ years of hands-on experience building and deploying LLM/AI applications in production environments
• Proven track record of deploying applications serving 10,000+ concurrent users
• Continuous professional experience with no employment gaps or overlapping positions

Technical Expertise

LLM & AI Frameworks:

• Deep hands-on experience with LLM APIs (OpenAI, Claude, Gemini)
• Proficiency in LangGraph for building stateful, multi-actor AI applications
• Experience with DSPy for programmatic LLM optimization
• Strong understanding of MCP server integration and tool-use patterns
• Expertise in prompt engineering, chain-of-thought reasoning, and agent orchestration

Vector Databases & Semantic Search:

• Production experience with vector databases (Qdrant, Milvus, Pgvector)
• Understanding of embedding models, similarity search, and retrieval optimization
• Experience with hybrid search strategies combining vector and keyword approaches

Backend Development:

• Expert-level proficiency in Python with FastAPI for building high-performance microservices
• Strong experience with asynchronous programming using asyncio
• Real-time communication implementation using WebSockets (socket.io)
• Experience orchestrating complex I/O operations for high-concurrency requests

Message Queues & Task Management:

• Hands-on experience with message queue systems: Celery, RabbitMQ, or AWS SQS
• Understanding of distributed task processing and job scheduling

Database Technologies:

• Proficiency with PostgreSQL including advanced query optimization
• Experience with MongoDB for document storage
• Familiarity with Databricks and Iceberg for data lakehouse architectures

DevOps & Infrastructure:

• Strong understanding of Kubernetes for running scalable microservices
• Knowledge of pod autoscaling, resource limits, and service mesh patterns
• Experience with Azure DevOps for CI/CD pipeline management
• Understanding of containerization with Docker

Development Practices:

• Solid grasp of Agile/Scrum methodologies
• Experience with version control (Git) and collaborative development workflows
• Strong debugging and performance optimization skills.

Preferred Qualifications

Experience building and optimizing RAG (Retrieval-Augmented Generation) pipelines

Knowledge of MLOps practices and AI model deployment strategies

Hands-on experience with GoLang for high-performance services

Exposure to multi-cloud environments (Azure, AWS, GCP)

Experience with Kubernetes operators and custom resource definitions

Understanding of AI safety, guardrails, and responsible AI practices

Familiarity with observability tools (Prometheus, Grafana, ELK stack)

Experience with A/B testing and experimentation frameworks for AI systems

Technical Environment

• Languages:

  Python (primary), GoLang (preferred)

• Frameworks:

  FastAPI, LangGraph, DSPy

• LLM APIs:

  OpenAI, Claude, Gemini

• Vector DBs:

  Qdrant, Milvus, Pgvector

• Databases:

  PostgreSQL, MongoDB, Databricks, Iceberg

• Message Queues:

  Celery, RabbitMQ, AWS SQS

• Infrastructure:

  Kubernetes, Docker, Azure DevOps

• Real-time:

  WebSockets (socket.io), asyncio