Artificial Intelligence Engineer

Company:

Location:

Experience:

About Sparrow Risk Management

Sparrow

Role Overview

As one of our AI-focused engineers, you will be at the forefront of building intelligent, LLM-powered applications from the ground up. You will have full ownership of the AI development lifecycle from designing agentic workflows and building RAG pipelines to productionizing robust backend services. This is a high-impact role for a hands-on builder who loves to ship, experiment, and solve complex problems in a fast-paced startup environment.

Key Responsibilities

• Design, build, and iterate LLM-powered workflows (retrieval, routing, tool use, function calling, multi-step agents).
• Implement agentic apps that can plan, call tools/APIs, and maintain state across complex tasks.
• Build and optimize end-to-end RAG pipelines: including data ingestion, chunking, embeddings, indexing, and latency-optimized retrieval.
• Own prompt engineering & evaluation (A/B tests, guardrails, metrics for latency, cost, quality, and safety).
• Productionize models and workflows with robust observability (traces, tokens, failures), cost controls, and fallbacks (e.g., using Langsmith or similar tools).
• Ship backend services and APIs (e.g., Python/FastAPI) that integrate with our data stores and vector DBs.
• Collaborate closely with product and leadership to translate business requirements into reliable, user-facing features.

Must-Have Skills & Qualifications

• 1-3 years of professional software development experience.
• Btech in CSE or Relevant fields from Tier 1,2 Colleges in India.
• Hands-on experience with LLMs (OpenAI, Claude, Llama, etc.) and orchestration frameworks (LangChain, LlamaIndex, or custom).
• Strong Python proficiency. Experience building RESTful services and writing clean, tested, production-ready code.
• Proven experience with RAG, vector databases (e.g., Pinecone, Weaviate, FAISS, Qdrant), and embeddings.
• Strong understanding of agent patterns (tool calling, planning/execution, memory) and workflow engines.
• Familiarity with prompt design, safety/guardrails, and evaluation frameworks.
• Basics of cloud & deployment (AWS/GCP/Azure), Docker, Git, and CI/CD.
• A strong debugging mindset and a bias to ship and iterate quickly.
• Familiarity with MCP is a big plus.