AI Engineer - LangChain

Are you passionate about building next-generation AI agents that combine perception, reasoning, and autonomous action?

We are seeking an AI Developer with deep expertise in agentic AI frameworks-LangChain, LangGraph, CrewAI, or equivalents-who can take vision and language models from prototype to production at scale.

What You'll Do :

- Agentic AI Frameworks : Architect multi-agent workflows with role hierarchies, state graphs, and tool integrations.

- Vision & Image Models : Build and fine-tune CNN/ViT models for image classification, detection, OCR, and data extraction.

- LLMs & RAG : Fine-tune open-weight LLMs (LoRA/QLoRA, PEFT) and implement domain-specific RAG pipelines with vector databases.

- Deep Learning at Scale : Develop training pipelines in PyTorch/TensorFlow, deploy via TorchServe, Triton, or KServe.

- MLOps & APIs : Build robust AI microservices (FastAPI/gRPC), CI/CD workflows, and monitoring (Prometheus/Grafana).

- Performance Optimization : Optimize inference using ONNX/TensorRT, quantization, and edge deployment strategies.

- Collaboration : Work closely with product teams and mentor junior engineers.

What We're Looking For :

- Expertise in LangChain, LangGraph, CrewAI, or similar agentic AI tools.

- Hands-on experience in CNN/ViT, OCR, PyTorch/TensorFlow, and vector databases (FAISS, Weaviate, pgvector).

- Experience with LLM fine-tuning (LoRA/QLoRA, SFT, DPO, RLHF) and RAG pipelines.

- Solid understanding of MLOps, CI/CD, Kubernetes, and cloud platforms (AWS/GCP/Azure).

- Strong background in model optimization (ONNX/TensorRT) and production deployment.