AI Engineer

We are looking for an AI/ML Engineer (SDE2) to build and operate production-grade AI systems focused on LLMs, RAG, retrieval, memory, and personalization. This role is ideal for an engineer with strong Python and software engineering fundamentals who has hands-on experience building and deploying real-world AI applications—not just notebooks, prototypes, or basic LLM API integrations.

Responsibilities:

• Build production-ready LLM and conversational AI applications.
• Develop RAG pipelines, embeddings, and vector search and retrieval systems.
• Build long-term memory and user-profile systems for personalized experiences.
• Develop LLM orchestration pipelines involving retrieval, reasoning, tool calls, and response generation.
• Work on personalization, user intelligence, ranking, and recommendation systems.
• Improve AI quality through evaluation datasets, regression testing, and production metrics.
• Optimize LLM usage, latency, inference cost, and response quality.
• Build reliable Python services and APIs and take AI features from design → development → deployment → monitoring.
• Debug production issues and improve system scalability, reliability, and performance.

Requirements:

• 3-6 years of experience in software engineering, AI/ML engineering, applied ML, NLP, or related roles.
• Strong Python and software engineering fundamentals.
• Hands-on experience with LLMs, generative AI, NLP, or AI/ML applications.
• Practical experience with RAG, retrieval, embeddings, vector search, or context selection.
• Experience building backend services and integrating AI into production applications.
• Experience with production deployment, Docker, and AWS/cloud.
• Understanding of AI evaluation, system design, latency, cost, and reliability.
• Strong ownership mindset with the ability to take features from problem definition through production.

Good to Have:

• Qdrant, pgvector, or other vector databases.
• Neo4j / knowledge graphs / graph-based retrieval.
• LangChain / LlamaIndex.
• Redis, PostgreSQL, S3, queues, and asynchronous processing.
• Hugging Face, vLLM, fine-tuning, or model optimization.
• Recommendation systems, ranking, or user modeling.
• Langfuse or LLM observability/evaluation tools.
• Multilingual or Indic NLP.
• Experience with personalization or conversational memory.

Ideal Candidate:

• We are looking for someone who enjoys solving problems at the intersection of software engineering, applied ML, and LLMs and has experience taking AI features beyond prototypes into reliable, scalable production systems.
• Key Skills: Python, LLM, RAG, generative AI, NLP, embeddings, vector search, retrieval, conversational AI, personalization, memory, LangChain, LlamaIndex, Qdrant, pgvector, Docker, AWS, ML evaluation.