Job Title : AI Engineer (LLM & GenAI)

Level : Mid-Level (2 to 5 years experience)

Our client is looking for an ambitious AI Engineer with hands-on experience building, deploying, and evaluating LLM-powered applications to join our core product and engineering team in India.

Role Overview :

As a AI Engineer, you will bridge the gap between AI prototyping and robust, production-grade software. You will be responsible for building end-to-end LLM features from prompt engineering and Retrieval-Augmented Generation (RAG) architecture to fine-tuning open-source models, latency optimization, and agentic workflows. You will work closely with cross-functional product managers, full-stack engineers, and backend teams to ship high-impact GenAI features directly to production.

Key Responsibilities :

- LLM Integration & Architecture : Design and build production-ready LLM applications using commercial APIs (OpenAI, Anthropic) and open-source foundation models (Llama, Mistral).

- RAG & Search Systems : Build and optimize end-to-end Retrieval-Augmented Generation pipelines using vector search engines (Pinecone, Qdrant, Weaviate, pgvector), chunking strategies, and hybrid search mechanics.

- Agentic Workflows : Orchestrate multi-step AI agents, function calling, and tool-use frameworks (e.g., LangGraph, AutoGen, CrewAI) for complex, non-linear tasks.

- Model Fine-Tuning : Apply PEFT/LoRA, fine-tuning, and quantization techniques to optimize open-source models for domain-specific production use cases.

- Evaluation & Monitoring : Build evaluation frameworks (hallucination detection, cost tracking, accuracy, latency) using tools like Ragas or TruLens to ensure high-quality AI outputs.

- Backend Integration : Wrap AI workflows into high-performance REST or gRPC APIs (FastAPI/Python) and deploy via Docker/Kubernetes in cloud environments (AWS/GCP/Azure).

Qualifications & Requirements :

Must-Haves :

- Experience : 2 to 6 years of experience in software engineering, machine learning, or backend development, with at least 1 - 2 years directly dedicated to building with LLMs/Generative AI.

- Core Stack : Strong proficiency in Python (PyTorch, NumPy, Pandas) and async backend development (FastAPI/Flask).

- GenAI Tools : Hands-on experience with LLM frameworks (LangChain, LlamaIndex) and model orchestration.

- Vector DBs : Practical experience working with vector databases (Pinecone, Chroma, Qdrant, or pgvector).

- Engineering Fundamentals : Sound understanding of REST APIs, Git workflows, microservices, and CI/CD pipelines.

Nice-to-Haves / Plusses :

- Bachelors or Masters degree in Computer Science, Data Science, or related quantitative fields (IITs/NITs/BITS or equivalent tier-1 institutes preferred).

- Experience with agentic frameworks (LangGraph, CrewAI).

- Exposure to cloud AI platforms (AWS Bedrock/SageMaker, GCP Vertex AI, Azure OpenAI).

- Experience using LLM observability tools (LangSmith, Arize Phoenix).