Lead AI/ML Engineer

Job Summary

We are looking for an experienced ML Engineer / MLOps Engineer with strong expertise in building and deploying Large Language Model (LLM) applications in production environments. The ideal candidate will have hands-on experience in developing scalable AI systems, implementing RAG architectures, and ensuring performance, security, and reliability of LLM-based solutions.

Key Responsibilities

• Production Application Development
• Lead the end-to-end lifecycle of LLM applications, transforming prototypes into scalable, reliable, and production-ready systems.
• LLM API Integration & Orchestration
• Design and implement integrations with LLM APIs (e.g., OpenAI, Anthropic, internal models) with a focus on performance, cost optimization, and reliability.
• Prompt Engineering & Optimization
• Develop and refine advanced prompt strategies to ensure high-quality, accurate, and context-aware outputs.
• Context Management & RAG Implementation
• Build and optimize Retrieval-Augmented Generation (RAG) systems using vector databases and memory frameworks to improve response relevance.
• Output Validation & Quality Assurance
• Create validation pipelines to verify model outputs, reduce hallucinations, and ensure compliance with defined quality standards.
• AI Security & Risk Mitigation
• Implement safeguards against vulnerabilities such as prompt injection, indirect injection, and SQL injection across LLM applications.
• Production Deployment & Monitoring
• Deploy solutions using MLOps best practices across cloud platforms (AWS, GCP, Azure) and monitor performance, latency, token usage, and drift.

Required Skills & Qualifications

• Experience 5+ years of experience as an ML Engineer / MLOps Engineer
• Proven experience in deploying LLM applications into production environments

Technical Skills

• Strong proficiency in Python
• Experience with ML frameworks such as PyTorch or TensorFlow
• Hands-on experience with orchestration tools like Kubeflow or Airflow
• Experience with cloud platforms (AWS, GCP, or Azure)
• Knowledge of containerization (Docker, Kubernetes)
• Experience with vector databases (Pinecone, Weaviate, Chroma)
• Familiarity with RAG architectures and MLOps tools

LLM Expertise

• Strong understanding of LLM capabilities, limitations, and prompt engineering
• Awareness of security risks and mitigation strategies in generative AI

Core Competencies

• Strong problem-solving and analytical skills
• Ability to troubleshoot production-level issues (latency, performance, stability)
• Excellent communication and collaboration skills