Applied AI Engineer - LangChain/LangGraph

About the Role: We are seeking an Applied AI Engineer to bridge the gap between state-of-the-art machine learning models and scalable production software. In this role, you will design, build, and deploy production-grade AI solutions, leveraging Large Language Models (LLMs), Generative AI, and modern ML engineering pipelines to solve real-world customer problems. Key Responsibilities: - Integrate LLMs, foundational models, and custom ML pipelines into core software products. - Build, optimize, and maintain RAG (Retrieval-Augmented Generation) architectures, vector search indexes, and autonomous agent workflows. - Optimize model inference for latency, cost, and throughput via caching, quantization, and batching strategies. - Collaborate with product and backend teams to build RESTful APIs and microservices powering AI features. - Establish evaluation frameworks, monitoring, and guardrails to ensure model output accuracy, safety, and reliability in production. Required Qualifications: - Bachelor's or Master's degree in Computer Science, Data Science, AI, or a related field. - Min 1 year of software engineering experience with direct production exposure to AI/ML applications. - Strong proficiency in Python and backend development frameworks (e.g., FastAPI, Flask, or Django). - Hands-on experience with LLM orchestration frameworks (LangChain, LlamaIndex, or AutoGen) and APIs (OpenAI, Anthropic, Hugging Face). - Practical experience working with vector databases (Pinecone, Qdrant, Milvus, Weaviate, or Chroma). - Solid understanding of software engineering fundamentals: Git, Docker, REST APIs, and database design. Good to Have: - Experience fine-tuning LLMs using techniques like PEFT, LoRA, or QLoRA. - Exposure to MLOps tools and platforms (MLflow, Weights & Biases, BentoML, or vLLM). - Familiarity with cloud services (AWS Bedrock/SageMaker, GCP Vertex AI, or Azure OpenAI). - Experience with AI evaluation and benchmarking tools (e.g., Ragas, DeepEval). What We Offer: - Competitive salary package with equity options. - Budget for cloud compute resources and access to cutting-edge AI hardware/APIs. - Fast-tracked career growth with direct ownership of high-impact AI products. - Flexible work environment, health insurance, and learning stipend for AI certifications and conferences.