Senior LLM Engineer
We're looking for a Senior LLM Engineer to design, build, and scale production-grade AI applications powered by Large Language Models.
In this role, you'll work on architecting intelligent systems, evaluating approaches such as Prompt Engineering, RAG, Fine-Tuning, Agents, and Multi-Model Orchestration, and making technical decisions that balance performance, cost, reliability, and business impact.
What You'll Do
• Build and deploy LLM-powered applications using LangChain, LlamaIndex, and related frameworks
• Integrate with leading model providers including OpenAI, Anthropic, Gemini, Hugging Face, and Ollama
• Design and optimize RAG pipelines, retrieval systems, embeddings, and vector databases
• Implement observability, evaluation frameworks, monitoring, and cost optimization strategies
• Ensure security, reliability, scalability, and production readiness of AI systems
• Collaborate closely with Product, Data, and ML teams to deliver business-focused AI solutions
What We're Looking For
• 4+ years of software engineering experience building production systems
• 2+ years of hands-on experience developing LLM or AI-powered applications
• Strong Python expertise and experience with FastAPI, Django, or similar frameworks
• Experience with RAG architectures, vector databases, prompt engineering, and LLM APIs
• Solid software engineering fundamentals including testing, CI/CD, API design, Docker, and Kubernetes
Preferred Experience
• LangChain, LlamaIndex, GPT-4, Claude, Gemini, or equivalent ecosystems
• MLOps, monitoring, model versioning, and drift management
• Fine-tuning techniques such as LoRA and QLoRA
• Open-source contributions within the AI/LLM ecosystem
⚠️ Important: This is a senior-level role requiring prior experience building and deploying LLM applications in production environments. Freshers and candidates without relevant professional experience are unlikely to be considered for this position.
If you're passionate about building reliable, AI-powered cybersecurity platforms and solving complex real-world challenges with LLMs, we'd love to connect.