Key Responsibilities
* Architect and scale *AI-enabled search* systems for high-relevance semantic discovery across our product pipelines.
* Build *chat-based data insight* tools that allow users to query complex datasets via natural language.
* Prototype and deploy *Agentic AI* workflows to automate multi-step user workflows.
* Implement strict *AI Guardrails* to enforce safety, content policy, prompt injection defense, and structured data outputs.
* Establish continuous *LLM Evaluation* pipelines to benchmark accuracy, hallucination rates, and RAG retrieval performance.
* Drive *Model Optimization* techniques (caching, quantization, model selection, and prompt optimization) to minimize API latency and inference costs.
* Collaborate closely with our core engineering team to ship production-ready APIs and microservices.
Qualifications
* 2–4 years of software engineering experience focusing on Machine Learning, NLP, or LLM application engineering.
* Strong proficiency in *Python* and *TypeScript*.
* Production backend framework experience in both ecosystems (e.g., FastAPI, Flask, Node.js, Express, or NestJS).
* Hands-on experience with LLM orchestration (LangChain, LlamaIndex) and vector databases (Pinecone, Qdrant, Milvus, or Pgvector).
* Familiarity with guardrail frameworks (e.g., NeMo Guardrails, Guardrails AI, or Llama Guard) and evaluation suites (e.g., Ragas, TruLens, DeepEval).
* Demonstrated ability to optimize inference pipelines for cost, memory footprint, and speed.
* Startup mindset: comfortable context-switching across 4 distinct products in a fast-paced environment.
Pay: ₹600,000.00 - ₹1,000,000.00 per year
Work Location: In person
