Healthians - Senior AI Engineer - LLM/RAG

Position : Senior AI Engineer

Location : Gurgaon, Work from Office

Employment Type : Full-time

About the Role :

We are seeking a skilled Generative AI Engineer to design, develop, and deploy next-generation AI applications powered by LLMs, RAG pipelines, and agentic AI frameworks. The role requires strong expertise in backend development and front-end integration for AI Projects where work will happen at the intersection of AI research and production engineering to bring innovative, user-facing AI products to life. As a Senior AI Engineer, you will also be responsible for architecting scalable GenAI systems, mentoring engineers, designing robust AI infrastructure, and driving adoption of modern LLM frameworks and agentic systems across products.

Key Responsibilities :

- Build and fine-tune LLM-powered applications using GPT models and open-source alternatives.

- Design and implement RAG (Retrieval-Augmented Generation) pipelines for domain-specific AI use cases.

- Develop and maintain AI agents capable of autonomous task execution and reasoning.

- Integrate speech-to-text (STT), transcription, and TTS (Text-to-Speech) systems for real-time analytics.

- Implement call analytics solutions (intent detection, sentiment analysis, conversation summarization).

- Write efficient, production-grade Python code for AI pipelines and backend services.

- Collaborate with product and design teams to create intuitive React-based front-ends for AI apps.

- Deploy solutions on cloud with scalability, monitoring, and MLOps best practices.

- Stay up to date with the latest trends in Generative AI, agentic systems, and multimodal AI.

- Lead the design and implementation of advanced RAG architectures, including hybrid search, reranking models, and semantic retrieval strategies.

- Build agentic workflows and multi-agent systems using modern orchestration frameworks.

- Design prompt engineering strategies including prompt chaining, structured outputs, guardrails, and evaluation frameworks.

- Integrate LLM-based services into backend systems via microservices architectures and API-first design.

- Design high-performance AI inference pipelines supporting low latency and high throughput.

- Lead AI architecture decisions and mentor junior engineers in best practices for production AI systems.

- Collaborate with backend, and DevOps teams to build end-to-end AI platforms.

- Implement AI workflow orchestration, tool usage, and reasoning pipelines for complex automation use cases.

Required Qualifications :

- Bachelors/Masters degree in Computer Science, AI/ML, Data Science, or related field.

- 47+ years of experience in AI/ML engineering, backend development, or GenAI systems

- Strong coding skills in Python (FastAPI, Flask, LangChain, LlamaIndex, Hugging Face).

- Experience with LLMs (OpenAI GPT, Anthropic Claude, Llama, Mistral, etc.).

- Hands-on knowledge of RAG architectures (vector databases like Pinecone, Weaviate, FAISS, Milvus).

- Familiarity with React.js for building AI-driven web applications.

- Understanding of speech technologies (ASR/STT, TTS engines).

- Strong foundation in API development & integration.

- Deep expertise in Generative AI frameworks such as LangChain, LlamaIndex, Semantic Kernel, and similar orchestration tools.

- Strong experience designing Retrieval-Augmented Generation (RAG) pipelines, vector search architectures, and semantic indexing strategies.

- Experience working with embedding models, reranking models, and vector databases.

- Hands-on experience with modern LLM APIs and open-source models including GPT-4/4o, Claude, Llama 3, Mixtral, Mistral, and other foundation models.

- Experience implementing agent-based AI systems, autonomous workflows, and tool-calling architectures.

- Strong understanding of prompt engineering techniques, prompt evaluation, and hallucination mitigation strategies.

- Experience deploying AI systems using containerized environments (Docker, Kubernetes) and cloud infrastructure.

- Familiarity with AI model monitoring, evaluation metrics, and production deployment patterns.

What We Offer :

- Opportunity to build cutting-edge Generative AI products for real-world healthcare applications.

- Access to the latest LLM and agentic AI frameworks.

- Competitive salary, benefits, and continuous learning opportunities.

- Opportunity to work on large-scale AI systems, agentic automation platforms, and next-generation GenAI products.