Full Stack AI Engineer

About The Opportunity

• Design and implement full-stack features that integrate LLMs/ML models into web and API-driven products—end-to-end from UX to inference.
• Build and maintain backend inference services and RAG pipelines (embedding, vector search, retrieval, prompt orchestration) with strong SLAs.
• Develop responsive front-end components (React/TypeScript) and connect them to secure, well-documented APIs for AI workflows.
• Productionise models: containerise, deploy, automate CI/CD, and tune autoscaling, latency and cost for inference at scale.
• Collaborate with ML researchers and product teams to define experiments, implement evaluation metrics, and roll successful models to production.
• Implement observability, monitoring, and alerting for model performance, data drift, and system reliability; enforce security and privacy best practices.
  

Skills & Qualifications

Must-Have

• 3+ years building full-stack applications with strong backend experience in Python (FastAPI/Flask) and front-end experience in React/TypeScript.
• Hands-on experience integrating and productionising LLMs/GenAI (OpenAI/HuggingFace) and implementing RAG patterns with vector search.
• Proficiency with containerisation (Docker), CI/CD pipelines, and deploying services to cloud platforms (AWS/GCP/Azure).
• Practical knowledge of ML frameworks (PyTorch or TensorFlow) and exposure to model serving frameworks or MLOps tools.
• Experience building scalable APIs (REST/gRPC), working with SQL and NoSQL datastores, and implementing secure data handling.
• Strong debugging, testing (unit/integration), Git-centred workflows and documentation skills.
  

Preferred

• Experience with vector DBs and libraries (FAISS, Milvus, Pinecone) and embedding pipelines.
• Familiarity with Kubernetes, autoscaling, infra-as-code (Terraform), and cloud-native monitoring (Prometheus/Grafana).
• Knowledge of prompt engineering, evaluation for RAG, and optimisation for low-latency inference.
• Prior work in SaaS or product companies shipping customer-facing AI features at scale.
  

• Fully remote (India) role with flexible hours and asynchronous collaboration.
• High-impact product work: visibility to leadership and opportunity to own end-to-end AI features.
• Learning & growth budget, access to AI tooling, and a collaborative team culture focused on engineering excellence.